计算机视觉论文-2021-06-09_sitong.wu论文

本专栏是计算机视觉方向论文收集积累，时间：2021年6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: Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning
AUTHORS: Sixing Yin ; Yameng Han ; Shufang Li
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a new iterative refined interactive segmentation method for medical images based on agent reinforcement learning, which focuses on the problem of target segmentation boundaries.

2, TITLE: Conversational Fashion Image Retrieval Via Multiturn Natural Language Feedback
AUTHORS: Yifei Yuan ; Wai Lam
CATEGORY: cs.CV [cs.CV, cs.IR]
HIGHLIGHT: We propose a novel framework that can effectively handle conversational fashion image retrieval with multiturn natural language feedback texts.

3, TITLE: Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
AUTHORS: BOWEN SHI et. al.
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we for the first time propose a unified framework, termed as Multi-Dataset Pretraining, to take full advantage of the fragmented annotations of different datasets.

4, TITLE: Learning By Distillation: A Self-Supervised Learning Framework for Optical Flow Estimation
AUTHORS: Pengpeng Liu ; Michael R. Lyu ; Irwin King ; Jia Xu
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: We present DistillFlow, a knowledge distillation approach to learning optical flow.

5, TITLE: Few-Shot Action Localization Without Knowing Boundaries
AUTHORS: Ting-Ting Xie ; Christos Tzelepis ; Fan Fu ; Ioannis Patras
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we go a step further and show that it is possible to learn to localize actions in untrimmed videos when a) only one/few trimmed examples of the target action are available at test time, and b) when a large collection of videos with only class label annotation (some trimmed and some weakly annotated untrimmed ones) are available for training; with no overlap between the classes used during training and testing.

6, TITLE: Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
AUTHORS: Zhekai Du ; Jingjing Li ; Hongzu Su ; Lei Zhu ; Ke Lu
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG, cs.MM]
HIGHLIGHT: To challenge this issue, in this paper, we propose a cross-domain gradient discrepancy minimization (CGDM) method which explicitly minimizes the discrepancy of gradients generated by source samples and target samples.

7, TITLE: LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video Using Pose and Lighting Normalization
AUTHORS: Avisek Lahiri ; Vivek Kwatra ; Christian Frueh ; John Lewis ; Chris Bregler
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a video-based learning framework for animating personalized 3D talking faces from audio.

8, TITLE: Image2Point: 3D Point-Cloud Understanding with Pretrained 2D ConvNets
AUTHORS: CHENFENG XU et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.RO]
HIGHLIGHT: Our paper investigates the potential for transferability between these two representations by empirically investigating whether this approach works, what factors affect the transfer performance, and how to make it work even better.

9, TITLE: Progressive Spatio-Temporal Bilinear Network with Monte Carlo Dropout for Landmark-based Facial Expression Recognition with Uncertainty Estimation
AUTHORS: Negar Heidari ; Alexandros Iosifidis
CATEGORY: cs.CV [cs.CV, cs.CC, cs.HC]
HIGHLIGHT: In this paper, we propose a method which learns an optimized compact network topology for real-time facial expression recognition utilizing localized facial landmark features.

10, TITLE: Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation
AUTHORS: Gabriel Tjio ; Ping Liu ; Joey Tianyi Zhou ; Rick Siow Mong Goh
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose an adversarial hallucination approach, which combines a class-wise hallucination module and a semantic segmentation module.

11, TITLE: Image Deformation Estimation Via Multi-Objective Optimization
AUTHORS: Takumi Nakane ; Xuequan Lu ; Haoran Xie ; Chao Zhang
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we cast the registration task as a multi-objective optimization problem (MOP) according to the fact that regions affected by each control point overlap with each other.

12, TITLE: Data-Efficient Instance Generation from Instance Discrimination
AUTHORS: Ceyuan Yang ; Yujun Shen ; Yinghao Xu ; Bolei Zhou
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we propose a data-efficient Instance Generation (InsGen) method based on instance discrimination.

13, TITLE: Contrastive Representation Learning for Hand Shape Estimation
AUTHORS: Christian Zimmermann ; Max Argus ; Thomas Brox
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning.

14, TITLE: Simulated Adversarial Testing of Face Recognition Models
AUTHORS: NATANIEL RUIZ et. al.
CATEGORY: cs.CV [cs.CV, cs.AI, cs.CY, cs.LG]
HIGHLIGHT: In this work, we propose a framework for learning how to test machine learning algorithms using simulators in an adversarial manner in order to find weaknesses in the model before deploying it in critical scenarios.

15, TITLE: Scaling Vision Transformers
AUTHORS: Xiaohua Zhai ; Alexander Kolesnikov ; Neil Houlsby ; Lucas Beyer
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: As a result, we successfully train a ViT model with two billion parameters, which attains a new state-of-the-art on ImageNet of 90.45% top-1 accuracy.

16, TITLE: How to Design A Three-Stage Architecture for Audio-Visual Active Speaker Detection in The Wild
AUTHORS: Okan K�p�kl� ; Maja Taseska ; Gerhard Rigoll
CATEGORY: cs.CV [cs.CV, cs.LG, cs.SD, eess.AS]
HIGHLIGHT: Based on a series of controlled experiments, this work presents several practical guidelines for audio-visual active speaker detection.

17, TITLE: Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions
AUTHORS: Daniel Rosenberg ; Itai Gat ; Amir Feder ; Roi Reichart
CATEGORY: cs.CV [cs.CV, cs.CL, cs.LG]
HIGHLIGHT: Using these augmentations, we propose a new robustness measure, Robustness to Augmented Data (RAD), which measures the consistency of model predictions between original and augmented examples.

18, TITLE: Hierarchical Lov�sz Embeddings for Proposal-free Panoptic Segmentation
AUTHORS: TOMMI KEROLA et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In contrast, we propose Hierarchical Lov\'asz Embeddings, per pixel feature vectors that simultaneously encode instance- and category-level discriminative information.

19, TITLE: MoCo-Flow: Neural Motion Consensus Flow for Dynamic Humans in Stationary Monocular Cameras
AUTHORS: Xuelin Chen ; Weiyu Li ; Daniel Cohen-Or ; Niloy J. Mitra ; Baoquan Chen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we introduce Neural Motion Consensus Flow (MoCo-Flow), a representation that models the dynamic scene using a 4D continuous time-variant function.

20, TITLE: A Synchronized Reprojection-based Model for 3D Human Pose Estimation
AUTHORS: Yicheng Deng ; Cheng Sun ; Yongqi Sun ; Jiahui Zhu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a weakly supervised GAN-based model for 3D human pose estimation that considers 3D information along with 2D information simultaneously, in which a reprojection network is employed to learn the mapping of the distribution from 3D poses to 2D poses.

21, TITLE: Harnessing Unrecognizable Faces for Face Recognition
AUTHORS: Siqi Deng ; Yuanjun Xiong ; Meng Wang ; Wei Xia ; Stefano Soatto
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a measure of recognizability of a face image that leverages a key empirical observation: an embedding of face images, implemented by a deep neural network trained using mostly recognizable identities, induces a partition of the hypersphere whereby unrecognizable identities cluster together.

22, TITLE: Novel View Video Prediction Using A Dual Representation
AUTHORS: Sarah Shiraz ; Krishna Regmi ; Shruti Vyas ; Yogesh S. Rawat ; Mubarak Shah
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We address the problem of novel view video prediction; given a set of input video clips from a single/multiple views, our network is able to predict the video from a novel view.

23, TITLE: Progressive Multi-scale Fusion Network for RGB-D Salient Object Detection
AUTHORS: Guangyu Ren ; Yanchu Xie ; Tianhong Dai ; Tania Stathaki
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we discuss about the advantages of the so-called progressive multi-scale fusion method and propose a mask-guided feature aggregation module(MGFA).

24, TITLE: SDGMNet: Statistic-based Dynamic Gradient Modulation for Local Descriptor Learning
AUTHORS: Jiayi Ma ; Yuxin Deng
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we propose a dynamic gradient modulation, named SDGMNet, to improve triplet loss for local descriptor learning.

25, TITLE: Subject-Independent Brain-Computer Interface for Decoding High-Level Visual Imagery Tasks
AUTHORS: Dae-Hyeok Lee ; Dong-Kyun Han ; Sung-Jin Kim ; Ji-Hoon Jeong ; Seong-Whan Lee
CATEGORY: cs.CV [cs.CV, cs.AI, eess.IV, q-bio.NC]
HIGHLIGHT: In this study, we proposed the subepoch-wise feature encoder (SEFE) to improve the performances in the subject-independent tasks by using the VI dataset.

26, TITLE: Design of Low-Artifact Interpolation Kernels By Means of Computer Algebra
AUTHORS: Peter Karpov
CATEGORY: cs.CV [cs.CV, cs.SC, eess.IV]
HIGHLIGHT: We present a number of new piecewise-polynomial kernels for image interpolation.

27, TITLE: HPRNet: Hierarchical Point Regression for Whole-Body Human Pose Estimation
AUTHORS: Nermin Samet ; Emre Akbas
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we present a new bottom-up one-stage method for whole-body pose estimation, which we name "hierarchical point regression," or HPRNet for short, referring to the network that implements this method.

28, TITLE: Interpreting Deep Learning Based Cerebral Palsy Prediction with Channel Attention
AUTHORS: Manli Zhu ; Qianhui Men ; Edmond S. L. Ho ; Howard Leung ; Hubert P. H. Shum
CATEGORY: cs.CV [cs.CV, cs.LG, eess.IV]
HIGHLIGHT: In this paper, we propose a channel attention module for deep learning models to predict cerebral palsy from infants' body movements, which highlights the key features (i.e. body joints) the model identifies as important, thereby indicating why certain diagnostic results are found.

29, TITLE: Fully Transformer Networks for Semantic ImageSegmentation
AUTHORS: Sitong Wu ; Tianyi Wu ; Fangjian Lin ; Shengwei Tian ; Guodong Guo
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we explore a novel framework for semantic image segmentation, which is encoder-decoder based Fully Transformer Networks (FTN).

30, TITLE: Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight
AUTHORS: QI HAN et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We rephrase local attention as a channel-wise locally-connected layer and analyze it from two network regularization manners, sparse connectivity and weight sharing, as well as weight computation.

31, TITLE: Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
AUTHORS: Bingfeng Zhang ; Jimin Xiao ; Jianbo Jiao ; Yunchao Wei ; Yao Zhao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we aim to tackle bounding box supervised semantic segmentation, i.e., training accurate semantic segmentation models using bounding box annotations as supervision.

32, TITLE: SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation
AUTHORS: Taehun Kim ; Jinseong Kim ; Daijin Kim
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: For this reason, we propose Spatial Context Memoization (SpaM), a bypassing branch for spatial context by retaining the input dimension and constantly communicating its spatial context and rich semantic information mutually with the backbone network.

33, TITLE: Segmentation and ABCD Rule Extraction for Skin Tumors Classification
AUTHORS: Mahammed Messadi ; Hocine Cherifi ; Abdelhafid Bessaid
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this work, we present an automated diagnosis system based on the ABCD rule used in clinical diagnosis in order to discriminate benign from malignant skin lesions.

34, TITLE: On The Role of Feedback in Visual Processing: A Predictive Coding Perspective
AUTHORS: Andrea Alamia ; Milad Mozafari ; Bhavin Choksi ; Rufin VanRullen
CATEGORY: cs.CV [cs.CV, q-bio.NC]
HIGHLIGHT: Several studies investigated the inclusion of top-down feedback connections in convolutional networks; however, it remains unclear how and when these connections are functionally helpful.

35, TITLE: Highly Accurate Digital Traffic Recording As A Basis for Future Mobility Research: Methods and Concepts of The Research Project HDV-Mess
AUTHORS: LAURENT KLOEKER et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Highly Accurate Digital Traffic Recording As A Basis for Future Mobility Research: Methods and Concepts of The Research Project HDV-Mess

36, TITLE: White Paper Assistance: A Step Forward Beyond The Shortcut Learning
AUTHORS: XUAN CHENG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To combat with this unintended propensity, we borrow the idea of printer test page and propose a novel approach called White Paper Assistance.

37, TITLE: On Improving Adversarial Transferability of Vision Transformers
AUTHORS: Muzammal Naseer ; Kanchana Ranasinghe ; Salman Khan ; Fahad Shahbaz Khan ; Fatih Porikli
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: (i) Self-Ensemble: We propose a method to find multiple discriminative pathways by dissecting a single ViT model into an ensemble of networks.

38, TITLE: On The Use of Automatically Generated Synthetic Image Datasets for Benchmarking Face Recognition
AUTHORS: Laurent Colbois ; Tiago de Freitas Pereira ; S�bastien Marcel
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: The work presented in this paper provides a study on benchmarking FR systems using a synthetic dataset.

39, TITLE: Weakly Supervised Volumetric Image Segmentation with Deformed Templates
AUTHORS: Udaranga Wickramasinghe ; Pascal Fua
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose an approach that is truly weakly-supervised in the sense that we only need to provide a sparse set of 3D point on the surface of target objects, an easy task that can be quickly done.

40, TITLE: Multi-task Transformation Learning for Robust Out-of-Distribution Detection
AUTHORS: Sina Mohseni ; Arash Vahdat ; Jay Yadawa
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a simple framework that leverages multi-task transformation learning for training effective representation for OOD detection which outperforms state-of-the-art OOD detection performance and robustness on several image datasets.

41, TITLE: SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation
AUTHORS: Ioannis Kazakos ; Carles Ventura ; Miriam Bellver ; Carina Silberer ; Xavier Giro-i-Nieto
CATEGORY: cs.CV [cs.CV, cs.CL, cs.MM]
HIGHLIGHT: Our experiments demonstrate that by training with our synthetic referring expressions one can improve the ability of a model to generalize across different datasets, without any additional annotation cost. To this end, we propose a novel method, namely SynthRef, for generating synthetic referring expressions for target objects in an image (or video frame), and we also present and disseminate the first large-scale dataset with synthetic referring expressions for video object segmentation.

42, TITLE: CSRNet: Cascaded Selective Resolution Network for Real-time Semantic Segmentation
AUTHORS: JINGJING XIONG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To tackle this problem, we propose a light Cascaded Selective Resolution Network (CSRNet) to improve the performance of real-time segmentation through multiple context information embedding and enhanced feature aggregation.

43, TITLE: Salvage of Supervision in Weakly Supervised Detection
AUTHORS: Lin Sui ; Chen-Lin Zhang ; Jianxin Wu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To bridge the gaps, this paper proposes a new framework, Salvage of Supervision (SoS), with the key idea being to harness every potentially useful supervisory signal in WSOD: the weak image-level labels, the pseudo-labels, and the power of semi-supervised object detection.

44, TITLE: RobustNav: Towards Benchmarking Robustness in Embodied Navigation
AUTHORS: Prithvijit Chattopadhyay ; Judy Hoffman ; Roozbeh Mottaghi ; Aniruddha Kembhavi
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: As an attempt towards assessing the robustness of embodied navigation agents, we propose RobustNav, a framework to quantify the performance of embodied navigation agents when exposed to a wide variety of visual - affecting RGB inputs - and dynamics - affecting transition dynamics - corruptions.

45, TITLE: On The Relation Between Statistical Learning and Perceptual Distances
AUTHORS: Alexander Hepburn ; Valero Laparra ; Raul Santos-Rodriguez ; Johannes Ball� ; Jes�s Malo
CATEGORY: cs.CV [cs.CV, eess.IV, q-bio.NC]
HIGHLIGHT: In this paper, we aim to unravel the non-trivial relationship between the probability distribution of the data, perceptual distances, and unsupervised machine learning.

46, TITLE: Semantically Controllable Scene Generation with Guidance of Explicit Knowledge
AUTHORS: Wenhao Ding ; Bo Li ; Kim Ji Eun ; Ding Zhao
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In this paper, we introduce a novel method to incorporate domain knowledge \textit{explicitly} in the generation process to achieve semantically controllable scene generation.

47, TITLE: LocalTrans: A Multiscale Local Transformer Network for Cross-Resolution Homography Estimation
AUTHORS: RUIZHI SHAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we consider the cross-resolution homography estimation as a multimodal problem, and propose a local transformer network embedded within a multiscale structure to explicitly learn correspondences between the multimodal inputs, namely, input images with different resolutions.

48, TITLE: MViT: Mask Vision Transformer for Facial Expression Recognition in The Wild
AUTHORS: Hanting Li ; Mingzhe Sui ; Feng Zhao ; Zhengjun Zha ; Feng Wu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: MViT: Mask Vision Transformer for Facial Expression Recognition in The Wild

49, TITLE: Self-Supervised Structure-from-Motion Through Tightly-Coupled Depth and Egomotion Networks
AUTHORS: Brandon Wagstaff ; Valentin Peretroukhin ; Jonathan Kelly
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: Toward this end, we introduce several notions of coupling, categorize existing approaches, and present a novel tightly-coupled approach that leverages the interdependence of depth and egomotion at training and at inference time.

50, TITLE: Low-Rank Subspaces in GANs
AUTHORS: JIAPENG ZHU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: By contrast, this work introduces low-rank subspaces that enable more precise control of GAN generation.

51, TITLE: Task-Generic Hierarchical Human Motion Prior Using VAEs
AUTHORS: JIAMAN LI et. al.
CATEGORY: cs.CV [cs.CV, cs.GR]
HIGHLIGHT: In this paper, we present a method for learning complex human motions independent of specific tasks using a combined global and local latent space to facilitate coarse and fine-grained modeling.

52, TITLE: Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
AUTHORS: YULIN LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address these issues, we propose a novel end-to-end Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoderdecoder architecture, including a pixel context based transformer encoder and a part prototype based transformer decoder.

53, TITLE: Variational AutoEncoder for Reference Based Image Super-Resolution
AUTHORS: Zhi-Song Liu ; Wan-Chi Siu ; Li-Wen Wang
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE).

54, TITLE: DETReg: Unsupervised Pretraining with Region Priors for Object Detection
AUTHORS: AMIR BAR et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Here, we present DETReg, an unsupervised pretraining approach for object DEtection with TRansformers using Region priors.

55, TITLE: Chasing Sparsity in Vision Transformers:An End-to-End Exploration
AUTHORS: TIANLONG CHEN et. al.
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In contrast, this paper aims to trim down both the training memory overhead and the inference complexity, without scarifying the achievable accuracy.

56, TITLE: Grapevine Winter Pruning Automation: On Potential Pruning Points Detection Through 2D Plant Modeling Using Grapevine Segmentation
AUTHORS: MIGUEL FERNANDES et. al.
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: To this end, this paper presents a novel multidisciplinary approach that tackles this challenging task by performing object segmentation on grapevine images, used to create a representative model of the grapevine plants.

57, TITLE: Discriminative Triad Matching and Reconstruction for Weakly Referring Expression Grounding
AUTHORS: Mingjie Sun ; Jimin Xiao ; Eng Gee Lim ; Si Liu ; John Y. Goulermas
CATEGORY: cs.CV [cs.CV, cs.MM]
HIGHLIGHT: In this paper, we are tackling the weakly-supervised referring expression grounding task, for the localization of a referent object in an image according to a query sentence, where the mapping between image regions and queries are not available during the training stage.

58, TITLE: Meta Learning for Knowledge Distillation
AUTHORS: Wangchunshu Zhou ; Canwen Xu ; Julian McAuley
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CL, cs.CV]
HIGHLIGHT: We present Meta Learning for Knowledge Distillation (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training.

59, TITLE: Generative Flows with Invertible Attentions
AUTHORS: Rhea Sanjay Sukthanker ; Zhiwu Huang ; Suryansh Kumar ; Radu Timofte ; Luc Van Gool
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: To fill the gap, in this paper, we introduce two types of invertible attention mechanisms for generative flow models.

60, TITLE: Provably Robust Detection of Out-of-distribution Data (almost) for Free
AUTHORS: Alexander Meinke ; Julian Bitterwolf ; Matthias Hein
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper we propose a novel method where from first principles we combine a certifiable OOD detector with a standard classifier into an OOD aware classifier.

61, TITLE: Manifold Topology Divergence: A Framework for Comparing Data Manifolds
AUTHORS: SERGUEI BARANNIKOV et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We describe a novel tool, Cross-Barcode(P,Q), that, given a pair of distributions in a high-dimensional space, tracks multiscale topology spacial discrepancies between manifolds on which the distributions are concentrated.

62, TITLE: Graph-MLP: Node Classification Without Message Passing in Graph
AUTHORS: YANG HU et. al.
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV, cs.SI]
HIGHLIGHT: Instead, we propose a pure multilayer-perceptron-based framework, Graph-MLP with the supervision signal leveraging graph structure, which is sufficient for learning discriminative node representation.

63, TITLE: FEAR: A Simple Lightweight Method to Rank Architectures
AUTHORS: Debadeepta Dey ; Shital Shah ; Sebastien Bubeck
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: We propose a simple but powerful method which we call FEAR, for ranking architectures in any search space.

64, TITLE: NWT: Towards Natural Audio-to-video Generation with Representation Learning
AUTHORS: Rayhane Mama ; Marc S. Tyndel ; Hashiam Kadhim ; Cole Clifford ; Ragavan Thurairatnam
CATEGORY: cs.SD [cs.SD, cs.AI, cs.CV, cs.LG, eess.AS]
HIGHLIGHT: In this work we introduce NWT, an expressive speech-to-video model.

65, TITLE: Object Based Attention Through Internal Gating
AUTHORS: Jordan Lei ; Ari S. Benjamin ; Konrad P. Kording
CATEGORY: q-bio.NC [q-bio.NC, cs.AI, cs.CV, cs.LG, cs.NE]
HIGHLIGHT: Here, we propose an artificial neural network model of object-based attention that captures the way in which attention is both top-down and recurrent.

66, TITLE: AutoPtosis
AUTHORS: Abdullah Aleem ; Manoj Prabhakar Nallabothula ; Pete Setabutr ; Joelle A. Hallak ; Darvin Yi
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we present AutoPtosis, an artificial intelligence based system with interpretable results for rapid diagnosis of ptosis.

67, TITLE: EnMcGAN: Adversarial Ensemble Learning for 3D Complete Renal Structures Segmentation
AUTHORS: YUTING HE et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this study, we utilize the adversarial ensemble learning and propose Ensemble Multi-condition GAN(EnMcGAN) for 3D CRS segmentation for the first time.

68, TITLE: PolypGen: A Multi-center Polyp Detection and Segmentation Dataset for Generalisability Assessment
AUTHORS: SHARIB ALI et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we provide comprehensive insight into data construction and annotation strategies, annotation quality assurance and technical validation for our extended EndoCV2021 dataset which we refer to as PolypGen.

69, TITLE: Generative Adversarial Network with Object Detector Discriminator for Enhanced Defect Detection on Ultrasonic B-scans
AUTHORS: Luka Posilovi? ; Duje Medak ; Marko Subasic ; Marko Budimir ; Sven Loncaric
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we present a novel deep learning Generative Adversarial Network model for generating ultrasonic B-scans with defects in distinct locations.