计算机视觉论文-2021-03-10_adaptive multi-teacher multi-level knowledge disti

本专栏是计算机视觉方向论文收集积累，时间：2021年3月9日，来源：paper digest

欢迎关注原创公众号 【计算机视觉联盟】，回复 【西瓜书手推笔记】 可获取我的机器学习纯手推笔记！

直达笔记地址：机器学习手推笔记（GitHub地址）

1, TITLE: Selective Replay Enhances Learning in Online Continual Analogical Reasoning
AUTHORS: Tyler L. Hayes ; Christopher Kanan
CATEGORY: cs.AI [cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we establish experimental baselines, protocols, and forward and backward transfer metrics to evaluate continual learners on RPMs.

2, TITLE: Semiotically-grounded Distant Viewing of Diagrams: Insights from Two Multimodal Corpora
AUTHORS: Tuomo Hiippala ; John A. Bateman
CATEGORY: cs.CL [cs.CL, cs.CV, cs.MM]
HIGHLIGHT: In this article, we bring together theories of multimodal communication and computational methods to study how primary school science diagrams combine multiple expressive resources.

3, TITLE: ES-Net: An Efficient Stereo Matching Network
AUTHORS: Zhengyu Huang ; Theodore B. Norris ; Panqu Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose the Efficient Stereo Network (ESNet), which achieves high performance and efficient inference at the same time.

4, TITLE: An Automated Approach to Mitigate Transcription Errors in Braille Texts for The Portuguese Language
AUTHORS: Andr� Roberto Ortoncelli ; Marlon Marcon ; Franciele Beal
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents an automated approach to mitigate transcription errors in braille texts for the Portuguese language.

5, TITLE: An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions
AUTHORS: Henrique Siqueira ; Pablo Barros ; Sven Magg ; Stefan Wermter
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we proposed an ensemble based on convolutional networks where the early layers are strong low-level feature extractors, and their representations shared with an ensemble of convolutional branches.

6, TITLE: Attention-Enhanced Cross-Task Network for Analysing Multiple Attributes of Lung Nodules in CT
AUTHORS: Xiaohang Fu ; Lei Bi ; Ashnil Kumar ; Michael Fulham ; Jinman Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this study, we address these challenges with a new convolutional neural network (CNN)-based MTL model that incorporates attention modules to simultaneously score 9 visual attributes of lung nodules in computed tomography (CT) image volumes.

7, TITLE: Deep Model Intellectual Property Protection Via Deep Watermarking
AUTHORS: JIE ZHANG et. al.
CATEGORY: cs.CV [cs.CV, cs.CR]
HIGHLIGHT: In this work, we propose a new model watermarking framework for protecting deep networks trained for low-level computer vision or image processing tasks.

8, TITLE: Predictive Visual Tracking: A New Benchmark and Baseline Approach
AUTHORS: Bowen Li ; Yiming Li ; Junjie Ye ; Changhong Fu ; Hang Zhao
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work, we aim to deal with a more realistic problem of latency-aware tracking.

9, TITLE: OPANAS: One-Shot Path Aggregation Network Architecture Search for Object
AUTHORS: Tingting Liang ; Yongtao Wang ; Guosheng Hu ; Zhi Tang ; Haibin Ling
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy.

10, TITLE: End-to-End Human Object Interaction Detection with HOI Transformer
AUTHORS: CHENG ZOU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner.

11, TITLE: Simple Online and Real-time Tracking with Occlusion Handling
AUTHORS: Mohammad Hossein Nasseri ; Hadi Moradi ; Reshad Hosseini ; Mohammadreza Babaee
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, a novel online multiple object tracking algorithm is presented that only uses geometric cues of objects to tackle the occlusion and reidentification challenges simultaneously.

12, TITLE: Improving Global Adversarial Robustness Generalization With Adversarially Trained GAN
AUTHORS: Desheng Wang ; Weidong Jin ; Yunpu Wu ; Aamir Khan
CATEGORY: cs.CV [cs.CV, cs.LG, I.2.10]
HIGHLIGHT: Experimental results in MNIST SVHN and CIFAR-10 datasets show that the proposed method doesn't rely on obfuscated gradients and achieves better global adversarial robustness generalization performance than the adversarially trained state-of-the-art CNNs.

13, TITLE: Unveiling The Potential of Structure-Preserving for Weakly Supervised Object Localization
AUTHORS: XINGJIA PAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a two-stage approach, termed structure-preserving activation (SPA), towards fully leveraging the structure information incorporated in convolutional features for WSOL.

14, TITLE: One-Shot Medical Landmark Detection
AUTHORS: Qingsong Yao ; Quan Quan ; Li Xiao ; S. Kevin Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To relieve such a burden for a landmark detection task, we explore the feasibility of using only a single annotated image and propose a novel framework named Cascade Comparing to Detect (CC2D) for one-shot landmark detection.

15, TITLE: Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets
AUTHORS: Pengbo Liu ; Li Xiao ; S. Kevin Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To unleash the potential behind these partially labeled, sequentially-constructed datasets, we propose to learn a multi-organ segmentation model through incremental learning (IL).

16, TITLE: FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
AUTHORS: Lingtong Kong ; Chunhua Shen ; Jie Yang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To deal with these challenges, in this paper, we dive into designing efficient structure for fast and accurate optical flow prediction.

17, TITLE: Imbalance-Aware Self-Supervised Learning for 3D Radiomic Representations
AUTHORS: HONGWEI LI et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this work, we address the challenge of learning representations of 3D medical images for an effective quantification under data imbalance.

18, TITLE: End-to-end Optimized Image Compression for Multiple Machine Tasks
AUTHORS: Lahiru D. Chamain ; Fabien Racap� ; Jean B�gaint ; Akshay Pushparaja ; Simon Feltman
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: For this purpose, we introduce 'Connectors' that are inserted between the decoder and the task algorithms to enable a direct transformation of the compressed content, which was previously optimized for a specific task, to multiple other machine tasks.

19, TITLE: LongReMix: Robust Learning with High Confidence Samples in A Noisy Label Environment
AUTHORS: Filipe R. Cordeiro ; Ragav Sachdeva ; Vasileios Belagiannis ; Ian Reid ; Gustavo Carneiro
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we hypothesise that the generalisation of such 2-stage noisy-label learning methods depends on the precision of the unsupervised classifier and the size of the training set to minimise the EVR.

20, TITLE: Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
AUTHORS: Bohan Wu ; Suraj Nair ; Roberto Martin-Martin ; Li Fei-Fei ; Chelsea Finn
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We introduce Greedy Hierarchical Variational Autoencoders (GHVAEs), a method that learns high-fidelity video predictions by greedily training each level of a hierarchical autoencoder.

21, TITLE: Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification
AUTHORS: Wenkang Li ; Ke Qi ; Wenbin Chen ; Yicong Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this problem, we adopt the batch all triplet selection strategy, which selects all the possible triplets among samples to optimize instead of the hardest triplet.

22, TITLE: Virtual Normal: Enforcing Geometric Constraintsfor Accurate and Robust Depth Prediction
AUTHORS: Wei Yin ; Yifan Liu ; Chunhua Shen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we show the importance of the high-order 3D geometric constraints for depth prediction. To demonstrate the excellent generalizability of learning affine-invariant depth on diverse data with the virtual normal loss, we construct a large-scale and diverse dataset for training affine-invariant depth, termed Diverse Scene Depth dataset (DiverseDepth), and test on five datasets with the zero-shot test setting.

23, TITLE: MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection
AUTHORS: Vibashan VS ; Poojan Oza ; Vishwanath A. Sindagi ; Vikram Gupta ; Vishal M. Patel
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome this issue, in this work, we attempt to incorporate category information into the domain adaptation process by proposing Memory Guided Attention for Category-Aware Domain Adaptation (MeGA-CDA).

24, TITLE: Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering
AUTHORS: Qing Li ; Xiaojiang Peng ; Yu Qiao ; Qi Hao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we address the unsupervised person Re-ID with a conceptually novel yet simple framework, termed as Multi-label Learning guided self-paced Clustering (MLC).

25, TITLE: Deep Gradient Projection Networks for Pan-sharpening
AUTHORS: SHUANG XU et. al.
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: This paper develops a model-based deep pan-sharpening approach.

26, TITLE: Estimating and Improving Fairness with Adversarial Learning
AUTHORS: Xiaoxiao Li ; Ziteng Cui ; Yifan Wu ; Li Gu ; Tatsuya Harada
CATEGORY: cs.CV [cs.CV, cs.AI, cs.CY]
HIGHLIGHT: To tackle this issue, we propose an adversarial multi-task training strategy to simultaneously mitigate and detect bias in the deep learning-based medical image analysis system.

27, TITLE: Semi-supervised Domain Adaptation Based on Dual-level Domain Mixing for Semantic Segmentation
AUTHORS: Shuaijun Chen ; Xu Jia ; Jianzhong He ; Yongjie Shi ; Jianzhuang Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We focus on a more practical setting of semi-supervised domain adaptation (SSDA) where both a small set of labeled target data and large amounts of labeled source data are available.

28, TITLE: On Implicit Attribute Localization for Generalized Zero-Shot Learning
AUTHORS: Shiqi Yang ; Kai Wang ; Luis Herranz ; Joost van de Weijer
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, 1) we show that common ZSL backbones (without explicit attention nor part detection) can implicitly localize attributes, yet this property is not exploited.

29, TITLE: Interpretable Attention Guided Network for Fine-grained Visual Classification
AUTHORS: Zhenhuan Huang ; Xiaoyue Duan ; Bo Zhao ; Jinhu L� ; Baochang Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Interpretable Attention Guided Network for Fine-grained Visual Classification

30, TITLE: High-Resolution Segmentation of Tooth Root Fuzzy Edge Based on Polynomial Curve Fitting with Landmark Detection
AUTHORS: YUNXIANG LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we propose a model for high-resolution segmentation based on polynomial curve fitting with landmark detection (HS-PCL).

31, TITLE: CheXseen: Unseen Disease Detection for Deep Learning Interpretation of Chest X-rays
AUTHORS: Siyu Shi ; Ishaan Malhi ; Kevin Tran ; Andrew Y. Ng ; Pranav Rajpurkar
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: We systematically evaluate the performance of deep learning models in the presence of diseases not labeled for or present during training.

32, TITLE: Dual-Task Mutual Learning for Semi-Supervised Medical Image Segmentation
AUTHORS: Yichi Zhang ; Jicong Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel dual-task mutual learning framework for semi-supervised medical image segmentation.

33, TITLE: Student-Teacher Feature Pyramid Matching for Unsupervised Anomaly Detection
AUTHORS: Guodong Wang ; Shumin Han ; Errui Ding ; Di Huang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a simple yet powerful approach to this issue, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency.

34, TITLE: Robust Point Cloud Registration Framework Based on Deep Graph Matching
AUTHORS: Kexue Fu ; Shaolei Liu ; Xiaoyuan Luo ; Manning Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel deep graph matchingbased framework for point cloud registration.

35, TITLE: Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
AUTHORS: Jianzhong He ; Xu Jia ; Shuaijun Chen ; Jianzhuang Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel multi-source domain adaptation framework based on collaborative learning for semantic segmentation.

36, TITLE: You Only Learn Once: Universal Anatomical Landmark Detection
AUTHORS: Heqin Zhu ; Qingsong Yao ; Li Xiao ; S. Kevin Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, for the first time, we investigate the idea of "You Only Learn Once (YOLO)" and develop a universal anatomical landmark detection model to realize multiple landmark detection tasks with end-to-end training based on mixed datasets.

37, TITLE: Behavior-Driven Synthesis of Human Dynamics
AUTHORS: Andreas Blattmann ; Timo Milbich ; Michael Dorkenwald ; Bj�rn Ommer
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we present a model for human behavior synthesis which learns a dedicated representation of human dynamics independent of postures.

38, TITLE: Self-Augmented Multi-Modal Feature Embedding
AUTHORS: Shinnosuke Matsuo ; Seiichi Uchida ; Brian Kenji Iwana
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To exploit this fact, we propose the use of self-augmentation and combine it with multi-modal feature embedding.

39, TITLE: Time and Frequency Network for Human Action Detection in Videos
AUTHORS: Changhai Li ; Huawei Chen ; Jingqing Lu ; Yang Huang ; Yingying Liu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose an end-to-end network that considers the time and frequency features simultaneously, named TFNet.

40, TITLE: Watching You: Global-guided Reciprocal Learning for Video-based Person Re-identification
AUTHORS: Xuehu Liu ; Pingping Zhang ; Chenyang Yu ; Huchuan Lu ; Xiaoyun Yang
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To address above issues, in this paper, we propose a novel Global-guided Reciprocal Learning (GRL) framework for video-based person Re-ID.

41, TITLE: Consensus Maximisation Using Influences of Monotone Boolean Functions
AUTHORS: Ruwan Tennakoon ; David Suter ; Erchuan Zhang ; Tat-Jun Chin ; Alireza Bab-Hadiashar
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: Based on this observation, we present an iterative algorithm to perform consensus maximisation.

42, TITLE: IRON: Invariant-based Highly Robust Point Cloud Registration
AUTHORS: Lei Sun
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present IRON (Invariant-based global Robust estimation and OptimizatioN), a non-minimal and highly robust solution for point cloud registration with a great number of outliers among the correspondences.

43, TITLE: Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection
AUTHORS: Chia-Yu Hsu ; Wenwen Li
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Specifically, we introduce raster scan-order techniques to serialize 2D images into 1D sequence data, and then leverage a combined LSTM (Long, Short-Term Memory) and CTC (Connectionist Temporal Classification) network to achieve object localization based on a total count (of interested objects).

44, TITLE: Spatial-Spectral Feedback Network for Super-Resolution of Hyperspectral Imagery
AUTHORS: Enhai Liu ; Zhenjie Tang ; Bin Pan ; Zhenwei Shi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these issues, in this paper, we propose a novel Spatial-Spectral Feedback Network (SSFN) to refine low-level representations among local spectral bands with high-level information from global spectral bands.

45, TITLE: Fibrosis-Net: A Tailored Deep Convolutional Neural Network Design for Prediction of Pulmonary Fibrosis Progression from Chest CT Images
AUTHORS: ALEXANDER WONG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: Motivated by this, we introduce Fibrosis-Net, a deep convolutional neural network design tailored for the prediction of pulmonary fibrosis progression from chest CT images.

46, TITLE: Localization and Mapping Using Instance-specific Mesh Models
AUTHORS: Qiaojun Feng ; Yue Meng ; Mo Shan ; Nikolay Atanasov
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: Our contribution is an instance-specific mesh model of object shape that can be optimized online based on semantic information extracted from camera images.

47, TITLE: Simultaneously Localize, Segment and Rank The Camouflaged Objects
AUTHORS: YUNQIU LYU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we revisit this task and argue that explicitly modeling the conspicuousness of camouflaged objects against their particular backgrounds can not only lead to a better understanding about camouflage and evolution of animals, but also provide guidance to design more sophisticated camouflage techniques.

48, TITLE: Repurposing GANs for One-shot Semantic Part Segmentation
AUTHORS: Nontawat Tritrong ; Pitchaporn Rewatbowornwong ; Supasorn Suwajanakorn
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we test this hypothesis and propose a simple and effective approach based on GANs for semantic part segmentation that requires as few as one label example along with an unlabeled dataset.

49, TITLE: Fully Convolutional Geometric Features for Category-level Object Alignment
AUTHORS: Qiaojun Feng ; Nikolay Atanasov
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: This paper focuses on pose registration of different object instances from the same category.

50, TITLE: Bridging The Distribution Gap of Visible-Infrared Person Re-identification with Modality Batch Normalization
AUTHORS: Wenkang Li ; Qi Ke ; Wenbin Chen ; Yicong Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these problems, we propose a new batch normalization layer called Modality Batch Normalization (MBN), which normalizes each modality sub-mini-batch respectively instead of the whole mini-batch, and can reduce these distribution gap significantly.

51, TITLE: Snapshot Compressive Imaging: Principle, Implementation, Theory, Algorithms and Applications
AUTHORS: Xin Yuan ; David J. Brady ; Aggelos K. Katsaggelos
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Via novel optical designs, the 2D detector samples the HD data in a {\em compressive} manner; following this, algorithms are employed to reconstruct the desired HD data-cube.

52, TITLE: TransBTS: Multimodal Brain Tumor Segmentation Using Transformer
AUTHORS: WENXUAN WANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we for the first time exploit Transformer in 3D CNN for MRI Brain Tumor Segmentation and propose a novel network named TransBTS based on the encoder-decoder structure.

53, TITLE: Adaptive Multi-Teacher Multi-level Knowledge Distillation
AUTHORS: Yuang Liu ; Wei Zhang ; Jun Wang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To bridge this gap, we propose a novel adaptive multi-teacher multi-level knowledge distillation learning framework~(AMTML-KD), which consists two novel insights: (i) associating each teacher with a latent representation to adaptively learn instance-level teacher importance weights which are leveraged for acquiring integrated soft-targets~(high-level knowledge) and (ii) enabling the intermediate-level hints~(intermediate-level knowledge) to be gathered from multiple teachers by the proposed multi-group hint strategy.

54, TITLE: Improving Automated Sonar Video Analysis to Notify About Jellyfish Blooms
AUTHORS: Artjoms Gorpincenko ; Geoffrey French ; Peter Knight ; Mike Challiss ; Michal Mackiewicz
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, a number of enhancements are proposed to the part of the system that is responsible for object classification.

55, TITLE: Domain Adaptive Robotic Gesture Recognition with Unsupervised Kinematic-Visual Data Alignment
AUTHORS: Xueying Shi ; Yueming Jin ; Qi Dou ; Jing Qin ; Pheng-Ann Heng
CATEGORY: cs.CV [cs.CV, cs.LG, cs.RO]
HIGHLIGHT: In this paper, we propose a novel unsupervised domain adaptation framework which can simultaneously transfer multi-modality knowledge, i.e., both kinematic and visual data, from simulator to real robot.

56, TITLE: Panoptic Lintention Network: Towards Efficient Navigational Perception for The Visually Impaired
AUTHORS: Wei Mao ; Jiaming Zhang ; Kailun Yang ; Rainer Stiefelhagen
CATEGORY: cs.CV [cs.CV, cs.LG, cs.RO, eess.IV]
HIGHLIGHT: In this paper, we utilize panoptic segmentation to assist the navigation of visually impaired people by offering both things and stuff awareness in the proximity of the visually impaired efficiently.

57, TITLE: Learning to Generate 3D Shapes with Generative Cellular Automata
AUTHORS: Dongsu Zhang ; Changwoon Choi ; Jeonghwan Kim ; Young Min Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present a probabilistic 3D generative model, named Generative Cellular Automata, which is able to produce diverse and high quality shapes.

58, TITLE: Perception Framework Through Real-Time Semantic Segmentation and Scene Recognition on A Wearable System for The Visually Impaired
AUTHORS: Yingzhi Zhang ; Haoye Chen ; Kailun Yang ; Jiaming Zhang ; Rainer Stiefelhagen
CATEGORY: cs.CV [cs.CV, cs.RO, eess.IV]
HIGHLIGHT: As the scene information, including objectness and scene type, are important for people with visual impairment, in this work we present a multi-task efficient perception system for the scene parsing and recognition tasks.

59, TITLE: Learning Statistical Texture for Semantic Segmentation
AUTHORS: LANYUN ZHU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation.

60, TITLE: A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations
AUTHORS: Zhenwang Qin ; Wensheng Wang ; Karl-Heinz Dammer ; Leifeng Guo ; Zhen Cao
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: Deep learning algorithms dominantly use in modern computer vision tasks which require high computing time, memory footprint, and power consumption.

61, TITLE: Multimodal Representation Learning Via Maximization of Local Mutual Information
AUTHORS: RUIZHI LIAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose and demonstrate a representation learning approach by maximizing the mutual information between local features of images and text.

62, TITLE: U-DuDoNet: Unpaired Dual-domain Network for CT Metal Artifact Reduction
AUTHORS: Yuanyuan Lyu ; Jiajun Fu ; Cheng Peng ; S. Kevin Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To combine the advantages of both MAR methods, we propose an unpaired dual-domain network (U-DuDoNet) trained using unpaired data.

63, TITLE: Parser-Free Virtual Try-on Via Distilling Appearance Flows
AUTHORS: YUYING GE et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this problem, we propose a novel approach, "teacher-tutor-student" knowledge distillation, which is able to produce highly photo-realistic images without human parsing, possessing several appealing advantages compared to prior arts.

64, TITLE: CRLF: Automatic Calibration and Refinement Based on Line Feature for LiDAR and Camera in Road Scenes
AUTHORS: Tao Ma ; Zhizheng Liu ; Guohang Yan ; Yikang Li
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: To tackle these issues, we propose a novel method to calibrate the extrinsic parameter for LiDAR and camera in road scenes.

65, TITLE: Enhancing Transformation-based Defenses Against Adversarial Examples with First-Order Perturbations
AUTHORS: Haimin Zhang ; Min Xu
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: Based on this observation, we propose a method of counteracting adversarial perturbations to resist adversarial examples.

66, TITLE: Unsupervised Object-Based Transition Models for 3D Partially Observable Environments
AUTHORS: Antonia Creswell ; Rishabh Kabra ; Chris Burgess ; Murray Shanahan
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: We present a slot-wise, object-based transition model that decomposes a scene into objects, aligns them (with respect to a slot-wise object memory) to maintain a consistent order across time, and predicts how those objects evolve over successive frames.

67, TITLE: ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
AUTHORS: DONGXU LI et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this work, we propose a novel implicit method to learn spatial correspondence among blurry frames in the feature space.

68, TITLE: Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic Parsing
AUTHORS: Tianfei Zhou ; Wenguan Wang ; Si Liu ; Yi Yang ; Luc Van Gool
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: By formulating joint association as maximum-weight bipartite matching, a differentiable solution is developed to exploit projected gradient descent and Dykstra's cyclic projection algorithm.

69, TITLE: Robust Reflection Removal with Reflection-free Flash-only Cues
AUTHORS: Chenyang Lei ; Qifeng Chen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images.

70, TITLE: Hierarchical Self Attention Based Autoencoder for Open-Set Human Activity Recognition
AUTHORS: M Tanjid Hasan Tonmoy ; Saif Mahmud ; A K M Mahbubur Rahman ; M Ashraful Amin ; Amin Ahsan Ali
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: We conduct extensive leave one subject out validation experiments that indicate significantly improved robustness to noise and subject specific variability in body-worn sensor signals.

71, TITLE: High Perceptual Quality Image Denoising with A Posterior Sampling CGAN
AUTHORS: Guy Ohayon ; Theo Adrai ; Gregory Vaksman ; Michael Elad ; Peyman Milanfar
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this paper we propose a different perspective, aiming to produce sharp and visually pleasing denoised images that are still faithful to their clean sources.

72, TITLE: Look, Evolve and Mold: Learning 3D Shape Manifold Via Single-view Synthetic Data
AUTHORS: Qianyu Feng ; Yawei Luo ; Keyang Luo ; Yi Yang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome these difficulties, we propose a domain-adaptive network for single-view 3D reconstruction, dubbed LEM, to generalize towards the natural scenario by fulfilling several aspects: (1) Look: incorporating spatial structure from the single view to enhance the representation; (2) Evolve: leveraging the semantic information with unsupervised contrastive mapping recurring to the shape priors; (3) Mold: transforming into the desired stereo manifold with discernment and semantic knowledge.

73, TITLE: RFN-Nest: An End-to-end Residual Fusion Network for Infrared and Visible Images
AUTHORS: Hui Li ; Xiao-Jun Wu ; Josef Kittler
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a residual fusion network (RFN) which is based on a residual architecture to replace the traditional fusion approach.

74, TITLE: Learning Cycle-Consistent Cooperative Networks Via Alternating MCMC Teaching for Unsupervised Cross-Domain Translation
AUTHORS: Jianwen Xie ; Zilong Zheng ; Xiaolin Fang ; Song-Chun Zhu ; Ying Nian Wu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper studies the unsupervised cross-domain translation problem by proposing a generative framework, in which the probability distribution of each domain is represented by a generative cooperative network that consists of an energy-based model and a latent variable model.

75, TITLE: Learn to Differ: Sim2Real Small Defection Segmentation Network
AUTHORS: ZEXI CHEN et. al.
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this paper, we propose the network SSDS that learns a way of distinguishing small defections between two images regardless of the context, so that the network can be trained once for all.

76, TITLE: ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building
AUTHORS: Hyungtae Lim ; Sungwon Hwang ; Hyun Myung
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: To tackle the problem, this paper presents a novel static map building method called ERASOR, Egocentric RAtio of pSeudo Occupancy-based dynamic object Removal, which is fast and robust to motion ambiguity.

77, TITLE: Analysis of Convolutional Decoder for Image Caption Generation
AUTHORS: Sulabh Katiyar ; Samir Kumar Borgohain
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we analyse various aspects of Convolutional Neural Network based Decoders such as Network complexity and depth, use of Data Augmentation, Attention mechanism, length of sentences used during training, etc on performance of the model.

78, TITLE: Pose Discrepancy Spatial Transformer Based Feature Disentangling for Partial Aspect Angles SAR Target Recognition
AUTHORS: Zaidao Wen ; Jiaxiang Liu ; Zhunga Liu ; Quan Pan
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This letter presents a novel framework termed DistSTN for the task of synthetic aperture radar (SAR) automatic target recognition (ATR).

79, TITLE: Automatic Flare Spot Artifact Detection and Removal in Photographs
AUTHORS: Patricia Vitoria ; Coloma Ballester
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a robust computational method to automatically detect and remove flare spot artifacts.

80, TITLE: Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
AUTHORS: FENGXIANG YANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a unified framework to solve both problems.

81, TITLE: WebFace260M: A Benchmark Unveiling The Power of Million-Scale Deep Face Recognition
AUTHORS: ZHENG ZHU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we contribute a new million-scale face benchmark containing noisy 4M identities/260M faces (WebFace260M) and cleaned 2M identities/42M faces (WebFace42M) training data, as well as an elaborately designed time-constrained evaluation protocol.

82, TITLE: Synplex: A Synthetic Simulator of Highly Multiplexed Histological Images
AUTHORS: Daniel Jim�nez-S�nchez ; Mikel Ariz ; Carlos Ortiz-de-Sol�rzano
CATEGORY: cs.CV [cs.CV, q-bio.QM, q-bio.TO, I.6.3]
HIGHLIGHT: In this paper, we present Synplex, a simulation system able to generate multiplex immunostained in situ tissue images based on user-defined parameters.

83, TITLE: Indoor Future Person Localization from An Egocentric Wearable Camera
AUTHORS: JIANING QIU et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this work, a new egocentric dataset was constructed using a wearable camera, with 8,250 short clips of a targeted person either walking 1) toward, 2) away, or 3) across the camera wearer in indoor environments, or 4) staying still in the scene, and 13,817 person bounding boxes were manually labelled.

84, TITLE: NeRD: Neural Representation of Distribution for Medical Image Segmentation
AUTHORS: HANG ZHANG et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: Using NeRD, we propose an end-to-end deep learning model for medical image segmentation that can compensate the negative impact of feature distribution shifting issue caused by commonly used network operations such as padding and pooling.

85, TITLE: Learning to Predict Vehicle Trajectories with Model-based Planning
AUTHORS: Haoran Song ; Di Luan ; Wenchao Ding ; Michael Yu Wang ; Qifeng Chen
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this paper, we introduce a novel prediction framework called PRIME, which stands for Prediction with Model-based Planning.

86, TITLE: Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
AUTHORS: BOHAO LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we pro-pose a class margin equilibrium (CME) approach, with theaim to optimize both feature space partition and novel classreconstruction in a systematic way.

87, TITLE: Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images
AUTHORS: Chentian Li ; Chi Ma ; William W. Lu
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: Here, we introduced a 3D morphological operation residual block to extract morphological features in end-to-end deep learning models for semantic segmentation.

88, TITLE: PISE: Person Image Synthesis and Editing with Decoupled GAN
AUTHORS: Jinsong Zhang ; Kun Li ; Yu-Kun Lai ; Jingyu Yang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose PISE, a novel two-stage generative model for Person Image Synthesis and Editing, which is able to generate realistic person images with desired poses, textures, or semantic layouts.

89, TITLE: ClassSR: A General Framework to Accelerate Super-Resolution Networks By Data Characteristic
AUTHORS: Xiangtao Kong ; Hengyuan Zhao ; Yu Qiao ; Chao Dong
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: On this basis, we propose a new solution pipeline -- ClassSR that combines classification and SR in a unified framework.

90, TITLE: Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision
AUTHORS: Andrew Shin ; Masato Ishii ; Takuya Narihira
CATEGORY: cs.CV [cs.CV, cs.CL]
HIGHLIGHT: In this paper, we review some of the most critical milestones in the field, as well as overall trends on how transformer architecture has been incorporated into visuolinguistic cross-modal tasks.

91, TITLE: FEDS -- Filtered Edit Distance Surrogate
AUTHORS: Yash Patel ; Jiri Matas
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a procedure to robustly train a scene text recognition model using a learned surrogate of edit distance.

92, TITLE: Noisy Label Learning for Large-scale Medical Image Classification
AUTHORS: FENGBEI LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we adapt a state-of-the-art (SOTA) noisy-label multi-class training approach to learn a multi-label classifier for the dataset Chest X-ray14, which is a large scale dataset known to contain label noise in the training set.

93, TITLE: Interpolation of CT Projections By Exploiting Their Self-Similarity and Smoothness
AUTHORS: Davood Karimi ; Rabab K. Ward
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel sinogram interpolation algorithm.

94, TITLE: Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning
AUTHORS: ALI CHERAGHIAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we introduce a distillation algorithm to address the problem of FSCIL and propose to make use of semantic information during training.

95, TITLE: Unsupervised Pretraining for Object Detection By Patch Reidentification
AUTHORS: JIAN DING et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To bridge the performance gap, this work proposes a simple yet effective representation learning method for object detection, named patch re-identification (Re-ID), which can be treated as a contrastive pretext task to learn location-discriminative representation unsupervisedly, possessing appealing advantages compared to its counterparts.

96, TITLE: A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding
AUTHORS: Di Feng ; Yiyang Zhou ; Chenfeng Xu ; Masayoshi Tomizuka ; Wei Zhan
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this work, we show that it is possible to perform all perception tasks via a simple and efficient multi-task network.

97, TITLE: Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
AUTHORS: Jizong Peng ; Marco Pedersoli ; Christian Desrosiers
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a novel semi-supervised segmentation method that leverages mutual information (MI) on categorical distributions to achieve both global representation invariance and local smoothness.

98, TITLE: Content-Based Detection of Temporal Metadata Manipulation
AUTHORS: RAFAEL PADILHA et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we present the nascent problem of detecting timestamp manipulation.

99, TITLE: Sparse LiDAR and Stereo Fusion (SLS-Fusion) for Depth Estimationand 3D Object Detection
AUTHORS: Nguyen Anh Minh Mai ; Pierre Duthon ; Louahdi Khoudour ; Alain Crouzil ; Sergio A. Velastin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents SLS-Fusion, a new approach to fuse data from 4-beam LiDAR and a stereo camera via a neural network for depth estimation to achieve better dense depth maps and thereby improves 3D object detection performance.

100, TITLE: LOHO: Latent Optimization of Hairstyles Via Orthogonalization
AUTHORS: Rohit Saha ; Brendan Duke ; Florian Shkurti ; Graham W. Taylor ; Parham Aarabi
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: Therefore, we propose Latent Optimization of Hairstyles via Orthogonalization (LOHO), an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer.

101, TITLE: Machine-learning Based Methodologies for 3d X-ray Measurement, Characterization and Optimization for Buried Structures in Advanced Ic Packages
AUTHORS: RAMANPREET S PAHWA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper we will demonstrate how data acquired non-destructively with a 3D X-ray microscope can be enhanced and optimized using machine learning, and can then be used to measure, characterize and optimize the design and production of buried interconnects in advanced IC packages.

102, TITLE: From Hand-Perspective Visual Information to Grasp Type Probabilities: Deep Learning Via Ranking Labels
AUTHORS: MO HAN et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: To predict the probability distribution over grasps, we exploit the statistical model over label rankings to solve the permutation domain problems via a maximum likelihood estimation, utilizing the manually ranked lists of grasps as a new form of label.

103, TITLE: Relationship-based Neural Baby Talk
AUTHORS: Fan Fu ; Tingting Xie ; Ioannis Patras ; Sepehr Jalali
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a relationship-based neural baby talk (R-NBT) model to comprehensively investigate several types of pairwise object interactions by encoding each image via three different relationship-based graph attention networks (GATs).

104, TITLE: The Weakly-Labeled Rand Index
AUTHORS: Dylan Stewart ; Anna Hampton ; Alina Zare ; Jeff Dale ; James Keller
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this paper, a labeling approach and associated modified version of the Rand index for weakly-labeled data is introduced to address these issues.

105, TITLE: Domain Adaptive Egocentric Person Re-identification
AUTHORS: Ankit Choudhary ; Deepak Mishra ; Arnab Karmakar
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Machine learning models trained on the publicly available large scale re-ID datasets cannot be applied to egocentric re-ID due to the dataset bias problem.

106, TITLE: Data-driven Cloud Clustering Via A Rotationally Invariant Autoencoder
AUTHORS: Takuya Kurihana ; Elisabeth Moyer ; Rebecca Willett ; Davis Gilton ; Ian Foster
CATEGORY: cs.CV [cs.CV, physics.ao-ph]
HIGHLIGHT: As a step towards answering these questions, we describe an automated rotation-invariant cloud clustering (RICC) method that leverages deep learning autoencoder technology to organize cloud imagery within large datasets in an unsupervised fashion, free from assumptions about predefined classes.

107, TITLE: What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels
AUTHORS: Jeonghun Baek ; Yusuke Matsui ; Kiyoharu Aizawa
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we would like to reactivate STR with fewer labels by disproving the common knowledge.

108, TITLE: Deepfake Videos in The Wild: Analysis and Detection
AUTHORS: JIAMENG PU et. al.
CATEGORY: cs.CR [cs.CR, cs.CV]
HIGHLIGHT: Even if detection schemes are shown to perform well on existing datasets, it is unclear how well the methods generalize to real-world deepfakes. To bridge this gap in knowledge, we make the following contributions: First, we collect and present the largest dataset of deepfake videos in the wild, containing 1,869 videos from YouTube and Bilibili, and extract over 4.8M frames of content.

109, TITLE: Hidden Backdoor Attack Against Semantic Segmentation Models
AUTHORS: YIMING LI et. al.
CATEGORY: cs.CR [cs.CR, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we reveal that this threat could also happen in semantic segmentation, which may further endanger many mission-critical applications ($e.g.$, autonomous driving).

110, TITLE: F-CAD: A Framework to Explore Hardware Accelerators for Codec Avatar Decoding
AUTHORS: XIAOFAN ZHANG et. al.
CATEGORY: cs.AR [cs.AR, cs.CV]
HIGHLIGHT: To address these problems, we propose an automation framework, called F-CAD (Facebook Codec avatar Accelerator Design), to explore and deliver optimized hardware accelerators for codec avatar decoding.

111, TITLE: Exploring A Makeup Support System for Transgender Passing Based on Automatic Gender Recognition
AUTHORS: Toby Chong ; Nolwenn Maudet ; Katsuki Harima ; Takeo Igarashi
CATEGORY: cs.HC [cs.HC, cs.CV]
HIGHLIGHT: In contrast, we explore how such technologies could potentially be appropriated to support transgender practices and needs, especially in non-Western contexts like Japan.

112, TITLE: Spectral Tensor Train Parameterization of Deep Learning Layers
AUTHORS: ANTON OBUKHOV et. al.
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML]
HIGHLIGHT: We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context.

113, TITLE: Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
AUTHORS: Patrick Wenzel ; Torsten Sch�n ; Laura Leal-Taix� ; Daniel Cremers
CATEGORY: cs.LG [cs.LG, cs.CV, cs.RO]
HIGHLIGHT: In this paper, we consider the problem of obstacle avoidance in simple 3D environments where the robot has to solely rely on a single monocular camera.

114, TITLE: Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain
AUTHORS: Jinyu Tian ; Jiantao Zhou ; Yuanman Li ; Jia Duan
CATEGORY: cs.LG [cs.LG, cs.CR, cs.CV]
HIGHLIGHT: In this work, we reveal that normal examples (NEs) are insensitive to the fluctuations occurring at the highly-curved region of the decision boundary, while AEs typically designed over one single domain (mostly spatial domain) exhibit exorbitant sensitivity on such fluctuations.

115, TITLE: Efficient Model Performance Estimation Via Feature Histories
AUTHORS: Shengcao Cao ; Xiaofang Wang ; Kris Kitani
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this work, we aim to optimize this exploration-exploitation trade-off in the context of HPO and NAS for image classification by accurately approximating a model's maximal performance early in the training process.

116, TITLE: Routing Towards Discriminative Power of Class Capsules
AUTHORS: Haoyu Yang ; Shuhe Li ; Bei Yu
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To obtain better and faster convergence, we propose a routing algorithm that incorporates a regularized quadratic programming problem which can be solved efficiently.

117, TITLE: Auto-tuning of Deep Neural Networks By Conflicting Layer Removal
AUTHORS: David Peer ; Sebastian Stabinger ; Antonio Rodriguez-Sanchez
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we introduce a novel methodology to identify layers that decrease the test accuracy of trained models.

118, TITLE: Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
AUTHORS: Sam Bond-Taylor ; Adam Leach ; Yang Long ; Chris G. Willcocks
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML, 68T01 (Primary), 68T07 (Secondary), I.5.0; I.4.0; G.3]
HIGHLIGHT: In particular, this compendium covers energy-based models, variational autoencoders, generative adversarial networks, autoregressive models, normalizing flows, in addition to numerous hybrid approaches.

119, TITLE: Efficient Continual Adaptation for Generative Adversarial Networks
AUTHORS: Sakshi Varshney ; Vinay Kumar Verma ; Lawrence Carin ; Piyush Rai
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML]
HIGHLIGHT: We present a continual learning approach for generative adversarial networks (GANs), by designing and leveraging parameter-efficient feature map transformations.

120, TITLE: Simplicial Complex Representation Learning
AUTHORS: Mustafa Hajij ; Ghada Zamzmi ; Xuanting Cai
CATEGORY: cs.LG [cs.LG, cs.CG, cs.CV, math.AT, stat.ML]
HIGHLIGHT: In this work, we propose a method for simplicial complex-level representation learning that embeds a simplicial complex to a universal embedding space in a way that complex-to-complex proximity is preserved.

121, TITLE: Global Canopy Height Estimation with GEDI LIDAR Waveforms and Bayesian Deep Learning
AUTHORS: NICO LANG et. al.
CATEGORY: cs.LG [cs.LG, cs.CV, physics.ao-ph]
HIGHLIGHT: Here, we present a novel supervised machine learning approach to interpret GEDI waveforms and regress canopy top height globally.

122, TITLE: Convolution Neural Network Hyperparameter Optimization Using Simplified Swarm Optimization
AUTHORS: Wei-Chang Yeh ; Yi-Ping Lin ; Yun-Chia Liang ; Chyh-Ming Lai
CATEGORY: cs.NE [cs.NE, cs.CV, cs.LG]
HIGHLIGHT: Therefore, this study proposes the idea of applying Simplified Swarm Optimization (SSO) on the hyperparameter optimization of LeNet models while using MNIST, Fashion MNIST, and Cifar10 as validation.

123, TITLE: GANav: Group-wise Attention Network for Classifying Navigable Regions in Unstructured Outdoor Environments
AUTHORS: Tianrui Guan ; Divya Kothandaraman ; Rohan Chandra ; Dinesh Manocha
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: We present a new learning-based method for identifying safe and navigable regions in off-road terrains and unstructured environments from RGB images.

124, TITLE: Learning A State Representation and Navigation in Cluttered and Dynamic Environments
AUTHORS: David Hoeller ; Lorenz Wellhausen ; Farbod Farshidian ; Marco Hutter
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this work, we present a learning-based pipeline to realise local navigation with a quadrupedal robot in cluttered environments with static and dynamic obstacles.

125, TITLE: Autonomous Object Harvesting Using Synchronized Optoelectronic Microrobots
AUTHORS: CHRISTOPHER BENDKOWSKI et. al.
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: In this article, we describe an approach to automated targeting and path planning to enable open-loop control of multiple microrobots.

126, TITLE: Disambiguating Affective Stimulus Associations for Robot Perception and Dialogue
AUTHORS: HENRIQUE SIQUEIRA et. al.
CATEGORY: cs.RO [cs.RO, cs.CL, cs.CV]
HIGHLIGHT: In this paper, we utilize the NICO robot's appearance and capabilities to give the NICO the ability to model a coherent affective association between a perceived auditory stimulus and a temporally asynchronous emotion expression.

127, TITLE: Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
AUTHORS: R�MI LAUMONT et. al.
CATEGORY: stat.ME [stat.ME, cs.CV, eess.IV, math.ST, stat.ML, stat.TH, 65K10, 65K05, 65D18, 62F15, 62C10, 68Q25, 68U10, 90C26]
HIGHLIGHT: We introduce two algorithms: 1) PnP-ULA (Unadjusted Langevin Algorithm) for Monte Carlo sampling and MMSE inference; and 2) PnP-SGD (Stochastic Gradient Descent) for MAP inference.

128, TITLE: Graph-based Pyramid Global Context Reasoning with A Saliency-aware Projection for COVID-19 Lung Infections Segmentation
AUTHORS: HUIMIN HUANG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To tackle these issues, we propose a Graph-based Pyramid Global Context Reasoning (Graph-PGCR) module, which is capable of modeling long-range dependencies among disjoint infections as well as adapt size variation.

129, TITLE: Memory-efficient Learning for High-Dimensional MRI Reconstruction
AUTHORS: KE WANG et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: Here we use a memory-efficient learning (MEL) framework which favorably trades off storage with a manageable increase in computation during training.

130, TITLE: Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy
AUTHORS: Sharmin Majumder ; Nasser Kehtarnavaz
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: This paper presents a multitask deep learning model to detect all the five stages of diabetic retinopathy (DR) consisting of no DR, mild DR, moderate DR, severe DR, and proliferate DR. This multitask model consists of one classification model and one regression model, each with its own loss function.