计算机视觉论文-2021-07-07_learning semantic segmentation of large-scale poin

本专栏是计算机视觉方向论文收集积累，时间：2021年7月7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: Morphological Classification of Galaxies in S-PLUS Using An Ensemble of Convolutional Networks
AUTHORS: N. M. CARDOSO et. al.
CATEGORY: astro-ph.GA [astro-ph.GA, cs.CV, cs.LG]
HIGHLIGHT: In this work, we combine accurate visual classifications of the Galaxy Zoo project with \emph {Deep Learning} methods.

2, TITLE: A Visual Introduction to Gaussian Belief Propagation
AUTHORS: Joseph Ortiz ; Talfan Evans ; Andrew J. Davison
CATEGORY: cs.AI [cs.AI, cs.CV, cs.LG, cs.RO]
HIGHLIGHT: In this article, we present a visual introduction to Gaussian Belief Propagation (GBP), an approximate probabilistic inference algorithm that operates by passing messages between the nodes of arbitrarily structured factor graphs.

3, TITLE: VidLanKD: Improving Language Understanding Via Video-Distilled Knowledge Transfer
AUTHORS: Zineng Tang ; Jaemin Cho ; Hao Tan ; Mohit Bansal
CATEGORY: cs.CL [cs.CL, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: To overcome these limitations, we present VidLanKD, a video-language knowledge distillation method for improving language understanding.

4, TITLE: Mind Your Outliers! Investigating The Negative Impact of Outliers on Active Learning for Visual Question Answering
AUTHORS: Siddharth Karamcheti ; Ranjay Krishna ; Li Fei-Fei ; Christopher D. Manning
CATEGORY: cs.CL [cs.CL, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: To understand this discrepancy, we profile 8 active learning methods on a per-example basis, and identify the problem as collective outliers -- groups of examples that active learning methods prefer to acquire but models fail to learn (e.g., questions that ask about text in images or require external knowledge).

5, TITLE: Depth-supervised NeRF: Fewer Views and Faster Training for Free
AUTHORS: Kangle Deng ; Andrew Liu ; Jun-Yan Zhu ; Deva Ramanan
CATEGORY: cs.CV [cs.CV, cs.GR, cs.LG]
HIGHLIGHT: We propose DS-NeRF (Depth-supervised Neural Radiance Fields), a loss for learning neural radiance fields that takes advantage of readily-available depth supervision.

6, TITLE: IPOKE: Poking A Still Image for Controlled Stochastic Video Synthesis
AUTHORS: Andreas Blattmann ; Timo Milbich ; Michael Dorkenwald ; Bj�rn Ommer
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Therefore, we propose iPOKE - invertible Prediction of Object Kinematics - that, conditioned on an initial frame and a local poke, allows to sample object kinematics and establishes a one-to-one correspondence to the corresponding plausible videos, thereby providing a controlled stochastic video synthesis.

7, TITLE: UACANet: Uncertainty Augmented Context Attention for Polyp Semgnetaion
AUTHORS: Taehun Kim ; Hyemin Lee ; Daijin Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose Uncertainty Augmented Context Attention network (UACANet) for polyp segmentation which consider a uncertain area of the saliency map.

8, TITLE: A Deep-learning--based Multimodal Depth-aware Dynamic Hand Gesture Recognition System
AUTHORS: Hasan Mahmud ; Mashrur Mahmud Morshed ; Md. Kamrul Hasan
CATEGORY: cs.CV [cs.CV, cs.HC, cs.LG]
HIGHLIGHT: In this paper, we focus on dynamic hand gesture (DHG) recognition using depth quantized image features and hand skeleton joint points.

9, TITLE: Spatiotemporal Fusion in Remote Sensing
AUTHORS: Hessah Albanwan ; Rongjun Qin
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this chapter, we aim to discuss the theory of spatiotemporal fusion by investigating previous works, in addition to describing the basic concepts and some of its applications by summarizing our prior and ongoing works.

10, TITLE: Learning Disentangled Representation Implicitly Via Transformer for Occluded Person Re-Identification
AUTHORS: Mengxi Jia ; Xinhua Cheng ; Shijian Lu ; Jian Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To better eliminate interference from occlusions, we design a contrast feature learning technique (CFL) for better separation of occlusion features and discriminative ID features.

11, TITLE: Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
AUTHORS: Takehiko Ohkawa ; Takuma Yagi ; Atsushi Hashimoto ; Yoshitaka Ushiku ; Yoichi Sato
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose (i) foreground-aware image stylization and (ii) consensus pseudo-labeling for domain adaptation of hand segmentation.

12, TITLE: Predicate Correlation Learning for Scene Graph Generation
AUTHORS: LEITIAN TAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, a Predicate Correlation Learning (PCL) method for SGG is proposed to address the above two problems by taking the correlation between predicates into consideration.

13, TITLE: Semi-TCL: Semi-Supervised Track Contrastive Representation Learning
AUTHORS: WEI LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We implement this learning objective in a unified form following the spirit of constrastive loss.

14, TITLE: Coarse-to-fine Semantic Localization with HD Map for Autonomous Driving in Structural Scenes
AUTHORS: Chengcheng Guo ; Minjie Lin ; Heyang Guo ; Pengpeng Liang ; Erkang Cheng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a cost-effective vehicle localization system with HD map for autonomous driving that uses cameras as primary sensors.

15, TITLE: MSE Loss with Outlying Label for Imbalanced Classification
AUTHORS: Sota Kato ; Kazuhiro Hotta
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose mean squared error (MSE) loss with outlying label for class imbalanced classification.

16, TITLE: The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification
AUTHORS: UJJWAL BAID et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification

17, TITLE: Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
AUTHORS: QINGYONG HU et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.RO, eess.SP]
HIGHLIGHT: In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds.

18, TITLE: From General to Specific: Online Updating for Blind Super-Resolution
AUTHORS: SHANG LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these issues, we propose an online super-resolution (ONSR) method.

19, TITLE: Vision Xformers: Efficient Attention for Image Classification
AUTHORS: Pranav Jeevan ; Amit Sethi
CATEGORY: cs.CV [cs.CV, cs.AI, cs.CC, cs.LG, I.4.0; I.4.1; I.4.7; I.4.8; I.4.9; I.4.10; I.2.10; I.5.1; I.5.2; I.5.4]
HIGHLIGHT: We modify the ViT architecture to work on longer sequence data by replacing the quadratic attention with efficient transformers like Performer, Linformer and Nystr\"omformer of linear complexity creating Vision X-formers (ViX).

20, TITLE: Polarized Skylight Orientation Determination Artificial Neural Network
AUTHORS: Huaju Liang ; Hongyang Bai ; Ke Hu ; Xinbo Lv
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: This paper proposes an artificial neural network to determine orientation using polarized skylight.

21, TITLE: Confidence-based Out-of-Distribution Detection: A Comparative Study and Analysis
AUTHORS: Christoph Berger ; Magdalini Paschali ; Ben Glocker ; Konstantinos Kamnitsas
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we assess the capability of various state-of-the-art approaches for confidence-based OOD detection through a comparative study and in-depth analysis.

22, TITLE: GCN-Based Linkage Prediction for Face Clusteringon Imbalanced Datasets: An Empirical Study
AUTHORS: HUAFENG YANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To tacklethese problems, we evaluate the feasibility of thoseexisting methods for imbalanced image classifica-tion problem on graphs with extensive experiments,and present a new method to alleviate the imbal-anced labels and also augment graph representa-tions using a Reverse-Imbalance Weighted Sam-pling (RIWS) strategy, followed with insightfulanalyses and discussions.

23, TITLE: Memory-aware Curriculum Federated Learning for Breast Cancer Classification
AUTHORS: Amelia Jim�nez-S�nchez ; Mickael Tardy ; Miguel A. Gonz�lez Ballester ; Diana Mateus ; Gemma Piella
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we define a memory-aware curriculum learning method for the federated setting.

24, TITLE: Long-Short Transformer: Efficient Transformers for Language and Vision
AUTHORS: CHEN ZHU et. al.
CATEGORY: cs.CV [cs.CV, cs.CL, cs.LG, cs.MM]
HIGHLIGHT: In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks.

25, TITLE: TransformerFusion: Monocular RGB Scene Reconstruction Using Transformers
AUTHORS: Alja? Bo?i? ; Pablo Palafox ; Justus Thies ; Angela Dai ; Matthias Nie�ner
CATEGORY: cs.CV [cs.CV, cs.GR, cs.LG]
HIGHLIGHT: We introduce TransformerFusion, a transformer-based 3D scene reconstruction approach.

26, TITLE: Label Noise in Segmentation Networks : Mitigation Must Deal with Bias
AUTHORS: Eugene Vorontsov ; Samuel Kadoury
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this work, we explore biased and unbiased errors artificially introduced to brain tumour annotations on MRI data.

27, TITLE: Independent Encoder for Deep Hierarchical Unsupervised Image-to-Image Translation
AUTHORS: Kai Ye ; Yinru Ye ; Minqiang Yang ; Bin Hu
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: To address this issue, we propose a novel architecture, termed as IEGAN, which removes the encoder of each network and introduces an encoder that is independent of other networks.

28, TITLE: Generalizing Nucleus Recognition Model in Multi-source Images Via Pruning
AUTHORS: JIATONG CAI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel method to improve DG by searching the domain-agnostic subnetwork in a domain merging scenario.

29, TITLE: Neighbor-Vote: Improving Monocular 3D Object Detection Through Neighbor Distance Voting
AUTHORS: XIAOMENG CHU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a novel neighbor-voting method that incorporates neighbor predictions to ameliorate object detection from severely deformed pseudo-LiDAR point clouds.

30, TITLE: Point Cloud Registration Using Representative Overlapping Points
AUTHORS: LIFA ZHU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose ROPNet, a new deep learning model using Representative Overlapping Points with discriminative features for registration that transforms partial-to-partial registration into partial-to-complete registration.

31, TITLE: Feature Fusion Vision Transformer Fine-Grained Visual Categorization
AUTHORS: Jun Wang ; Xiaohan Yu ; Yongsheng Gao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we proposea novel pure transformer-based framework Feature Fusion Vision Transformer (FFVT)where we aggregate the important tokens from each transformer layer to compensate thelocal, low-level and middle-level information.

32, TITLE: Self-Adversarial Training Incorporating Forgery Attention for Image Forgery Localization
AUTHORS: Long Zhuo ; Shunquan Tan ; Bin Li ; Jiwu Huang
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: In this paper, we propose a self-adversarial training strategy and a reliable coarse-to-fine network that utilizes a self-attention mechanism to localize forged regions in forgery images.

33, TITLE: Double-Uncertainty Assisted Spatial and Temporal Regularization Weighting for Learning-based Registration
AUTHORS: ZHE XU et. al.
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this study, we propose a mean-teacher based registration framework.

34, TITLE: Stateless Actor-critic for Instance Segmentation with High-level Priors
AUTHORS: PAUL HILT et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We formulate the instance segmentation problem as graph partitioning and the actor critic predicts the edge weights driven by the rewards, which are based on the conformity of segmented instances to high-level priors on object shape, position or size.

35, TITLE: Combining EfficientNet and Vision Transformers for Video Deepfake Detection
AUTHORS: Davide Coccomini ; Nicola Messina ; Claudio Gennaro ; Fabrizio Falchi
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this study, we combine various types of Vision Transformers with a convolutional EfficientNet B0 used as a feature extractor, obtaining comparable results with some very recent methods that use Vision Transformers.

36, TITLE: Attention-based Adversarial Appearance Learning of Augmented Pedestrians
AUTHORS: Kevin Strauss ; Artem Savkin ; Federico Tombari
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a method that leverages the advantages of the augmentation process and adversarial training to synthesize realistic data for the pedestrian recognition task.

37, TITLE: On Robustness of Lane Detection Models to Physical-World Adversarial Attacks in Autonomous Driving
AUTHORS: Takami Sato ; Qi Alfred Chen
CATEGORY: cs.CV [cs.CV, cs.CR]
HIGHLIGHT: In this work, we conduct the first large-scale empirical study to evaluate the robustness of state-of-the-art lane detection methods under physical-world adversarial attacks in autonomous driving.

38, TITLE: Integrating Circle Kernels Into Convolutional Neural Networks
AUTHORS: Kun He ; Chao Li ; Yixiao Yang ; Gao Huang ; John E. Hopcroft
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: Motivated by this observation, we propose using circle kernels with isotropic receptive fields for the convolution, and our training takes approximately equivalent amount of calculation when compared with the corresponding CNN with square kernels.

39, TITLE: End-To-End Data-Dependent Routing in Multi-Path Neural Networks
AUTHORS: Dumindu Tissera ; Kasun Vithanage ; Rukshan Wijessinghe ; Subha Fernando ; Ranga Rodrigo
CATEGORY: cs.CV [cs.CV, 68T10, I.2; I.4; I.5]
HIGHLIGHT: Therefore, we propose the use of multi-path neural networks with data-dependent resource allocation among parallel computations within layers, which also lets an input to be routed end-to-end through these parallel paths.

40, TITLE: Embracing The Dark Knowledge: Domain Generalization Using Regularized Knowledge Distillation
AUTHORS: Yufei Wang ; Haoliang Li ; Lap-pui Chau ; Alex C. Kot
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a simple, effective, and plug-and-play training strategy named Knowledge Distillation for Domain Generalization (KDDG) which is built upon a knowledge distillation framework with the gradient filter as a novel regularization term.

41, TITLE: Detecting Outliers with Poisson Image Interpolation
AUTHORS: JEREMY TAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an alternative to image reconstruction-based and image embedding-based methods and propose a new self-supervised method to tackle pathological anomaly detection.

42, TITLE: Contrastive Multimodal Fusion with TupleInfoNCE
AUTHORS: YUNZE LIU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a method for representation learning of multimodal data using contrastive losses.

43, TITLE: Semantic Segmentation Alternative Technique: Segmentation Domain Generation
AUTHORS: Ana-Cristina Rogoz ; Radu Muntean ; Stefan Cobeli
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this project we propose an alternative semantic segmentation technique making use of Generative Adversarial Networks.

44, TITLE: Depth-Aware Multi-Grid Deep Homography Estimation with Contextual Correlation
AUTHORS: Lang Nie ; Chunyu Lin ; Kang Liao ; Shuaicheng Liu ; Yao Zhao
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we address the two problems simultaneously, by designing a contextual correlation layer, which can capture the long-range correlation on feature maps and flexibly be bridged in a learning framework.

45, TITLE: VolNet: Estimating Human Body Part Volumes from A Single RGB Image
AUTHORS: Fabian Leinen ; Vittorio Cozzolino ; Torsten Sch�n
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: By using Volnet and combining multiple stacked hourglass networks together with ResNeXt, our model correctly predicted the volume in ~82% of cases with a 10% tolerance threshold. We generated a synthetic, large-scale dataset of photo-realistic images of human bodies with a wide range of body shapes and realistic poses called SURREALvols.

46, TITLE: DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis
AUTHORS: Sanket Biswas ; Pau Riba ; Josep Llad�s ; Umapada Pal
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper presents a novel approach, called DocSynth, to automatically synthesize document images based on a given layout.

47, TITLE: Anomaly Detection Using Edge Computing in Video Surveillance System: Review
AUTHORS: Devashree R. Patrikar ; Mayur Rajram Parate
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we surveyed various methodologies developed to detect anomalies in intelligent video surveillance.

48, TITLE: Hyperspectral Pansharpening Based on Improved Deep Image Prior and Residual Reconstruction
AUTHORS: Wele Gedara Chaminda Bandara ; Jeya Maria Jose Valanarasu ; Vishal M. Patel
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In order to accurately estimate fine information, we propose a novel over-complete network, called HyperKite, which focuses on learning high-level features by constraining the receptive from increasing in the deep layers.

49, TITLE: CoReD: Generalizing Fake Media Detection with Continual Representation Using Distillation
AUTHORS: Minha Kim ; Shahroz Tariq ; Simon S. Woo
CATEGORY: cs.CV [cs.CV, cs.CR, cs.LG, cs.MM, I.4.9; I.5.4]
HIGHLIGHT: Therefore, in this work, we apply continuous learning to neural networks' learning dynamics, emphasizing its potential to increase data efficiency significantly.

50, TITLE: NRST: Non-rigid Surface Tracking from Monocular Video
AUTHORS: MARC HABERMANN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an efficient method for non-rigid surface tracking from monocular RGB videos.

51, TITLE: FloorLevel-Net: Recognizing Floor-Level Lines with Height-Attention-Guided Multi-task Learning
AUTHORS: Mengyang Wu ; Wei Zeng ; Chi-Wing Fu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work tackles the problem of locating floor-level lines in street-view images, using a supervised deep learning approach.

52, TITLE: Graph Convolution for Re-ranking in Person Re-identification
AUTHORS: YUQI ZHANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric.

53, TITLE: HybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration
AUTHORS: SHUAIZHENG YAN et. al.
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this paper, we propose a data- and physics-driven unsupervised architecture that learns underwater vision restoration from unpaired underwater-terrestrial images.

54, TITLE: LightFuse: Lightweight CNN Based Dual-exposure Fusion
AUTHORS: Ziyi Liu ; Jie Yang ; Orly Yadid-Pecht
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: To address the challenge, we propose LightFuse, a light-weight CNN-based algorithm for extreme dual-exposure image fusion, which can be implemented on various embedded computing platforms with limited power and hardware resources.

55, TITLE: Automatic Size and Pose Homogenization with Spatial Transformer Network to Improve and Accelerate Pediatric Segmentation
AUTHORS: GIAMMARCO LA BARBERA et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, eess.IV, stat.ML]
HIGHLIGHT: In this work, we propose a new CNN architecture that is pose and scale invariant thanks to the use of Spatial Transformer Network (STN).

56, TITLE: Adapting Vehicle Detector to Target Domain By Adversarial Prediction Alignment
AUTHORS: Yohei Koga ; Hiroyuki Miyazaki ; Ryosuke Shibasaki
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose novel domain adaptation technique for object detection that aligns prediction output space.

57, TITLE: An Ensemble Noise-Robust K-fold Cross-Validation Selection Method for Noisy Labels
AUTHORS: Yong Wen ; Marcus Kalander ; Chanfei Su ; Lujia Pan
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we present Ensemble Noise-robust K-fold Cross-Validation Selection (E-NKCVS) to effectively select clean samples from noisy data, solving the first problem.

58, TITLE: Connectivity Matters: Neural Network Pruning Through The Lens of Effective Sparsity
AUTHORS: Artem Vysogorets ; Julia Kempe
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this work, we adopt the lens of effective sparsity to reevaluate several recent pruning algorithms on common benchmark architectures (e.g., LeNet-300-100, VGG-19, ResNet-18) and discover that their absolute and relative performance changes dramatically in this new and more appropriate framework.

59, TITLE: Rethinking Positional Encoding
AUTHORS: Jianqiao Zheng ; Sameera Ramasinghe ; Simon Lucey
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we strive to broaden this understanding by showing that alternative non-Fourier embedding functions can indeed be used for positional encoding.

60, TITLE: Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering
AUTHORS: DUMINDU TISSERA et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, 68T10, 62H30, I.2; I.4; I.5]
HIGHLIGHT: In this paper, we realize mixture model-based clustering with a neural network where the final layer neurons, with the aid of an additional transformation, approximate cluster distribution outputs.

61, TITLE: A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition
AUTHORS: Nikhil Varma Keetha ; Michael Milford ; Sourav Garg
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: In this paper, we present a novel approach to deduce two key types of utility for VPR: the utility of visual cues `specific' to an environment, and to a particular place.

62, TITLE: Real-time Pose Estimation from Images for Multiple Humanoid Robots
AUTHORS: Arash Amini ; Hafez Farazi ; Sven Behnke
CATEGORY: cs.RO [cs.RO, cs.CV]
HIGHLIGHT: This paper examines different state-of-the-art pose estimation models and proposes a lightweight model that can work in real-time on humanoid robots in the RoboCup Humanoid League environment. Additionally, we present a novel dataset called the HumanoidRobotPose dataset.

63, TITLE: Learned Visual Navigation for Under-Canopy Agricultural Robots
AUTHORS: ARUN NARENTHIRAN SIVAKUMAR et. al.
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: We describe a system for visually guided autonomous navigation of under-canopy farm robots.

64, TITLE: Domain Adaptation Via CycleGAN for Retina Segmentation in Optical Coherence Tomography
AUTHORS: RICKY CHEN et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, I.4.0]
HIGHLIGHT: In this study, we investigated a learning-based approach of adapting the domain of a publicly available dataset, UK Biobank dataset (UKB).

65, TITLE: Differentially Private Federated Deep Learning for Multi-site Medical Image Segmentation
AUTHORS: ALEXANDER ZILLER et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: Collaborative machine learning techniques such as federated learning (FL) enable the training of models on effectively larger datasets without data transfer.

66, TITLE: Unsupervised Learning of MRI Tissue Properties Using MRI Physics Models
AUTHORS: Divya Varadarajan ; Katherine L. Bouman ; Andre van der Kouwe ; Bruce Fischl ; Adrian V. Dalca
CATEGORY: eess.IV [eess.IV, cs.CV, q-bio.NC, q-bio.QM]
HIGHLIGHT: In this work we propose an unsupervised deep-learning strategy that employs MRI physics to estimate all three tissue properties from a single multiecho MRI scan session, and generalizes across varying acquisition parameters.

67, TITLE: Exploring Deep Learning Methods for Real-Time Surgical Instrument Segmentation in Laparoscopy
AUTHORS: DEBESH JHA et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To this end, we evaluate and compare some popular deep learning methods that can be explored for the automated segmentation of surgical instruments in laparoscopy, an important step towards tool tracking.

68, TITLE: A Theory of The Distortion-Perception Tradeoff in Wasserstein Space
AUTHORS: Dror Freirich ; Tomer Michaeli ; Ron Meir
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we derive a closed form expression for this distortion-perception (DP) function for the mean squared-error (MSE) distortion and the Wasserstein-2 perception index.

69, TITLE: Unsupervised Knowledge-Transfer for Learned Image Reconstruction
AUTHORS: Riccardo Barbano ; Zeljko Kereta ; Andreas Hauptmann ; Simon R. Arridge ; Bangti Jin
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We present extensive experimental results on low-dose and sparse-view computed tomography, showing that the proposed framework significantly improves reconstruction quality not only visually, but also quantitatively in terms of PSNR and SSIM, and is competitive with several state-of-the-art supervised and unsupervised reconstruction techniques.

70, TITLE: A New Smart-cropping Pipeline for Prostate Segmentation Using Deep Learning Networks
AUTHORS: DIMITRIOS G. ZARIDIS et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In the present work we propose a DL-based pipeline for cropping the region around the prostate from MRI images to produce a more balanced distribution of the foreground pixels (prostate) and the background pixels and improve segmentation accuracy.

71, TITLE: Impact of Deep Learning-based Image Super-resolution on Binary Signal Detection
AUTHORS: Xiaohui Zhang ; Varun A. Kelkar ; Jason Granstedt ; Hua Li ; Mark A. Anastasio
CATEGORY: eess.IV [eess.IV, cs.CV, physics.med-ph]
HIGHLIGHT: In this study, we investigate the impact of DL-SR methods on binary signal detection performance.

72, TITLE: COVID-19 Pneumonia Severity Prediction Using Hybrid Convolution-Attention Neural Architectures
AUTHORS: Nam Nguyen ; J. Morris Chang
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: This study proposed a novel framework for COVID-19 severity prediction, which is a combination of data-centric and model-centric approaches.

73, TITLE: Detecting Hypo-plastic Left Heart Syndrome in Fetal Ultrasound Via Disease-specific Atlas Maps
AUTHORS: SAMUEL BUDD et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: We present an interpretable, atlas-learning segmentation method for automatic diagnosis of Hypo-plastic Left Heart Syndrome (HLHS) from a single `4 Chamber Heart' view image.

74, TITLE: Histogram of Cell Types: Deep Learning for Automated Bone Marrow Cytology
AUTHORS: ROHOLLAH MOOSAVI TAYEBI et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: The approach achieves high accuracy in region detection (0.97 accuracy and 0.99 ROC AUC), and cell detection and cell classification (0.75 mAP, 0.78 F1-score, Log-average miss rate of 0.31).

75, TITLE: Automated Age-related Macular Degeneration Area Estimation -- First Results
AUTHORS: Rokas Pe?iulis ; Mantas Luko?evi?ius ; Algimantas Kri??iukaitis ; Robertas Petrolis ; Dovil? Buteikien?
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, 68T07, 68T05, 68T45, 92C55, I.2.6; J.3]
HIGHLIGHT: This work aims to research an automatic method for detecting Age-related Macular Degeneration (AMD) lesions in RGB eye fundus images.