计算机视觉论文-2021-07-20

本专栏是计算机视觉方向论文收集积累，时间：2021年7月20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: Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning
AUTHORS: Sayak Paul ; Siddha Ganju
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: Our approach sets a high score on the public leaderboard for the ETCI competition with 0.7654 IoU.

2, TITLE: A Positive/Unlabeled Approach for The Segmentation of Medical Sequences Using Point-Wise Supervision
AUTHORS: Laurent Lejeune ; Raphael Sznitman
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To alleviate this problem, this work proposes a new method to efficiently segment medical imaging volumes or videos using point-wise annotations only.

3, TITLE: AS-MLP: An Axial Shifted MLP Architecture for Vision
AUTHORS: Dongze Lian ; Zehao Yu ; Xing Sun ; Shenghua Gao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: An Axial Shifted MLP architecture (AS-MLP) is proposed in this paper.

4, TITLE: Dynamic Convolution for 3D Point Cloud Instance Segmentation
AUTHORS: Tong He ; Chunhua Shen ; Anton van den Hengel
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution.

5, TITLE: A High-Performance Adaptive Quantization Approach for Edge CNN Applications
AUTHORS: Hsu-Hsun Chin ; Ren-Song Tsay ; Hsin-I Wu
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: In this paper, we hence introduce an adaptive high-performance quantization method to resolve the issue of biased activation by dynamically adjusting the scaling and shifting factors based on the task loss.

6, TITLE: Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
AUTHORS: Kai Zhu ; Yang Cao ; Wei Zhai ; Jie Cheng ; Zheng-Jun Zha
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this problem, we propose a novel incremental prototype learning scheme.

7, TITLE: GenRadar: Self-supervised Probabilistic Camera Synthesis Based on Radar Frequencies
AUTHORS: Carsten Ditzel ; Klaus Dietmayer
CATEGORY: cs.CV [cs.CV, cs.LG]
HIGHLIGHT: This work combines the complementary strengths of both sensor types in a unique self-learning fusion approach for a probabilistic scene reconstruction in adverse surrounding conditions.

8, TITLE: Woodscape Fisheye Semantic Segmentation for Autonomous Driving -- CVPR 2021 OmniCV Workshop Challenge
AUTHORS: Saravanabalagi Ramachandran ; Ganesh Sistu ; John McDonald ; Senthil Yogamani
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: In this paper, we provide a summary of the competition which attracted the participation of 71 global teams and a total of 395 submissions. We present the WoodScape fisheye semantic segmentation challenge for autonomous driving which was held as part of the CVPR 2021 Workshop on Omnidirectional Computer Vision (OmniCV).

9, TITLE: Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images
AUTHORS: Yijin Huang ; Li Lin ; Pujin Cheng ; Junyan Lyu ; Xiaoying Tang
CATEGORY: cs.CV [cs.CV, eess.IV]
HIGHLIGHT: In this work, we propose a self-supervised framework, namely lesion-based contrastive learning for automated diabetic retinopathy (DR) grading.

10, TITLE: Disentangling and Vectorization: A 3D Visual Perception Approach for Autonomous Driving Based on Surround-View Fisheye Cameras
AUTHORS: ZIZHANG WU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we manage to overcome and avoid the difficulty of acquiring the large scale of accurate 3D labeled truth data, by breaking down the 3D object detection task into some sub-tasks, such as vehicle's contact point detection, type classification, re-identification and unit assembling, etc.

11, TITLE: A Miniature Biological Eagle-Eye Vision System for Small Target Detection
AUTHORS: Shutai Wang ; Qiang Fu ; Yinhao Hu ; Chunhua Zhang ; Wei He
CATEGORY: cs.CV [cs.CV, cs.SY, eess.SY]
HIGHLIGHT: Inspired by the structural characteristics and physiological mechanism of eagle-eye, a miniature vision system is designed for small target detection in this paper.

12, TITLE: Image Fusion Transformer
AUTHORS: Vibashan VS ; Jeya Maria Jose Valanarasu ; Poojan Oza ; Vishal M. Patel
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Specifically, CNN-based methods perform image fusion by fusing local features.

13, TITLE: RAMS-Trans: Recurrent Attention Multi-scale Transformer ForFine-grained Image Recognition
AUTHORS: YUNQING HU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose the recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi-scale manner.

14, TITLE: Exploring Set Similarity for Dense Self-supervised Representation Learning
AUTHORS: ZHAOQING WANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this issue, in this paper, we propose to explore \textbf{set} \textbf{sim}ilarity (SetSim) for dense self-supervised representation learning.

15, TITLE: Joint Implicit Image Function for Guided Depth Super-Resolution
AUTHORS: Jiaxiang Tang ; Xiaokang Chen ; Gang Zeng
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Inspired by the recent progress in implicit neural representation, we propose to formulate the guided super-resolution as a neural implicit image interpolation problem, where we take the form of a general image interpolation but use a novel Joint Implicit Image Function (JIIF) representation to learn both the interpolation weights and values.

16, TITLE: RECIST-Net: Lesion Detection Via Grouping Keypoints on RECIST-based Annotation
AUTHORS: CONG XIE et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Considering that data in clinical routine (such as the DeepLesion dataset) are usually annotated with a long and a short diameter according to the standard of Response Evaluation Criteria in Solid Tumors (RECIST) diameters, we propose RECIST-Net, a new approach to lesion detection in which the four extreme points and center point of the RECIST diameters are detected.

17, TITLE: Co-Teaching: An Ark to Unsupervised Stereo Matching
AUTHORS: Hengli Wang ; Rui Fan ; Ming Liu
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: To overcome this drawback, in this paper, we propose CoT-Stereo, a novel unsupervised stereo matching approach.

18, TITLE: SCV-Stereo: Learning Stereo Matching from A Sparse Cost Volume
AUTHORS: Hengli Wang ; Rui Fan ; Ming Liu
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: To address this problem, we propose SCV-Stereo, a novel CNN architecture, capable of learning dense stereo matching from sparse cost volume (SCV) representations.

19, TITLE: LeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation
AUTHORS: Guoping Xu ; Xingrong Wu ; Xuan Zhang ; Xinwei He
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose LeViT-UNet, which integrates a LeViT Transformer module into the U-Net architecture, for fast and accurate medical image segmentation.

20, TITLE: Face.evoLVe: A High-Performance Face Recognition Library
AUTHORS: Qingzhong Wang ; Pengfei Zhang ; Haoyi Xiong ; Jian Zhao
CATEGORY: cs.CV [cs.CV, cs.AI, cs.MM]
HIGHLIGHT: In this paper, we develop face.evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition.

21, TITLE: Transductive Image Segmentation: Self-training and Effect of Uncertainty Estimation
AUTHORS: KONSTANTINOS KAMNITSAS et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We focus on the self-training framework and explore its potential for transduction.

22, TITLE: Unsupervised Embedding Learning from Uncertainty Momentum Modeling
AUTHORS: Jiahuan Zhou ; Yansong Tang ; Bing Su ; Ying Wu
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To handle these issues, we propose a novel solution to explicitly model and directly explore the uncertainty of the given unlabeled learning samples.

23, TITLE: YOLOX: Exceeding YOLO Series in 2021
AUTHORS: Zheng Ge ; Songtao Liu ; Feng Wang ; Zeming Li ; Jian Sun
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX.

24, TITLE: Feature Mining: A Novel Training Strategy for Convolutional Neural Network
AUTHORS: TIANSHU XIE et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a novel training strategy for convolutional neural network(CNN) named Feature Mining, that aims to strengthen the network's learning of the local feature.

25, TITLE: Precise Aerial Image Matching Based on Deep Homography Estimation
AUTHORS: Myeong-Seok Oh ; Yong-Ju Lee ; Seong-Whan Lee
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a deep homography alignment network to precisely match two aerial images by progressively estimating the various transformation parameters.

26, TITLE: VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
AUTHORS: DAWEI DU et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields.

27, TITLE: Joint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation
AUTHORS: Gun-Hee Lee ; Han-Bin Ko ; Seong-Whan Lee
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose an overall framework that jointly considers dermatological classification and uncertainty estimation together.

28, TITLE: Fully Automated Machine Learning Pipeline for Echocardiogram Segmentation
AUTHORS: Hang Duong Thi Thuy ; Tuan Nguyen Minh ; Phi Nguyen Van ; Long Tran Quoc
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper introduces a pipeline that relies on Active Learning to ease the labeling work and utilizes Neural Architecture Search's idea to design the adequate deep learning model automatically.

29, TITLE: PICASO: Permutation-Invariant Cascaded Attentional Set Operator
AUTHORS: Samira Zare ; Hien Van Nguyen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To address this limitation, we propose a permutation-invariant cascaded attentional set operator (PICASO).

30, TITLE: Video Crowd Localization with Multi-focus Gaussian Neighbor Attention and A Large-Scale Benchmark
AUTHORS: HAOPENG LI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To model spatial-temporal dependencies of human mobility, we propose a multi-focus Gaussian neighbor attention (GNA), which can effectively exploit long-range correspondences while maintaining the spatial topological structure of the input videos. Moreover, to facilitate future researches in this field, we introduce a large-scale crowded video benchmark named SenseCrowd, which consists of 60K+ frames captured in various surveillance scenarios and 2M+ head annotations.

31, TITLE: Compound Figure Separation of Biomedical Images with Side Loss
AUTHORS: TIANYUAN YAO et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a simple compound figure separation (SimCFS) framework that uses weak classification annotations from individual images.

32, TITLE: Heterogeneous Face Frontalization Via Domain Agnostic Learning
AUTHORS: Xing Di ; Shuowen Hu ; Vishal M. Patel
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose a domain agnostic learning-based generative adversarial network (DAL-GAN) which can synthesize frontal views in the visible domain from thermal faces with pose variations.

33, TITLE: Cell Detection in Domain Shift Problem Using Pseudo-Cell-Position Heatmap
AUTHORS: Hyeonwoo Cho ; Kazuya Nishimura ; Kazuhide Watanabe ; Ryoma Bise
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We propose an unsupervised domain adaptation method for cell detection using the pseudo-cell-position heatmap, where a cell centroid becomes a peak with a Gaussian distribution in the map.

34, TITLE: Semi-supervised Cell Detection in Time-lapse Images Using Temporal Consistency
AUTHORS: Kazuya Nishimura ; Hyeonwoo Cho ; Ryoma Bise
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: To overcome this problem, we propose a semi-supervised cell-detection method that effectively uses a time-lapse sequence with one labeled image and the other images unlabeled.

35, TITLE: Facial Expressions Recognition with Convolutional Neural Networks
AUTHORS: Subodh Lonkar
CATEGORY: cs.CV [cs.CV, cs.AI, cs.LG]
HIGHLIGHT: In this paper, we will be deep diving into implementing a system for recognition of facial expressions (FER) by leveraging neural networks, and more specifically, Convolutional Neural Networks (CNNs).

36, TITLE: Agent-Environment Network for Temporal Action Proposal Generation
AUTHORS: Viet-Khoa Vo-Ho ; Ngan Le ; Kashu Yamazaki ; Akihiro Sugimoto ; Minh-Triet Tran
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Based on the action definition that a human, known as an agent, interacts with the environment and performs an action that affects the environment, we propose a contextual Agent-Environment Network.

37, TITLE: Learning Point Embedding for 3D Data Processing
AUTHORS: Zhenpeng Chen
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we take a different approach.

38, TITLE: Double Similarity Distillation for Semantic Image Segmentation
AUTHORS: Yingchao Feng ; Xian Sun ; Wenhui Diao ; Jihao Li ; Xin Gao
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, motivated by the residual learning and global aggregation, we propose a simple yet general and effective knowledge distillation framework called double similarity distillation (DSD) to improve the classification accuracy of all existing compact networks by capturing the similarity knowledge in pixel and category dimensions, respectively.

39, TITLE: A Benchmark for Gait Recognition Under Occlusion Collected By Multi-Kinect SDAS
AUTHORS: Na Li ; Xinbo Zhao
CATEGORY: cs.CV [cs.CV, 68T01, I.2.10; I.5.1; I.5.4]
HIGHLIGHT: Besides, as human pose is less sensitive to occlusion than human appearance, we propose a novel gait recognition method SkeletonGait based on human dual skeleton model using a framework of siamese spatio-temporal graph convolutional networks (siamese ST-GCN). We collect a new gait recognition database called OG RGB+D database, which breaks through the limitation of other gait databases and includes multimodal gait data of various occlusions (self-occlusion, active occlusion, and passive occlusion) by our multiple synchronous Azure Kinect DK sensors data acquisition system (multi-Kinect SDAS) that can be also applied in security situations.

40, TITLE: Action Forecasting with Feature-wise Self-Attention
AUTHORS: Yan Bin Ng ; Basura Fernando
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: We present a new architecture for human action forecasting from videos.

41, TITLE: UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
AUTHORS: DI YANG et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this context, we introduce UNIK, a novel skeleton-based action recognition method that is not only effective to learn spatio-temporal features on human skeleton sequences but also able to generalize across datasets.

42, TITLE: A Systematical Solution for Face De-identification
AUTHORS: Songlin Yang ; Wei Wang ; Yuehua Cheng ; Jing Dong
CATEGORY: cs.CV [cs.CV, cs.AI]
HIGHLIGHT: In different tasks, people have various requirements for face de-identification (De-ID), so we propose a systematical solution compatible for these De-ID operations.

43, TITLE: CodeMapping: Real-Time Dense Mapping for Sparse SLAM Using Compact Scene Representations
AUTHORS: Hidenobu Matsuki ; Raluca Scona ; Jan Czarnowski ; Andrew J. Davison
CATEGORY: cs.CV [cs.CV, cs.RO]
HIGHLIGHT: We propose a novel dense mapping framework for sparse visual SLAM systems which leverages a compact scene representation.

44, TITLE: OODformer: Out-Of-Distribution Detection Transformer
AUTHORS: Rajat Koner ; Poulami Sinhamahapatra ; Karsten Roscher ; Stephan G�nnemann ; Volker Tresp
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: This paper proposes a first-of-its-kind OOD detection architecture named OODformer that leverages the contextualization capabilities of the transformer.

45, TITLE: Non-binary Deep Transfer Learning for Imageclassification
AUTHORS: Jo Plested ; Xuyang Shen ; Tom Gedeon
CATEGORY: cs.CV [cs.CV, I.4.9; I.5.2]
HIGHLIGHT: We present methods for non-binary transfer learning including combining L2SP and L2 regularization and performing non-traditional fine-tuning hyperparameter searches.

46, TITLE: InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation
AUTHORS: DAHU SHI et. al.
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: Different from previous solutions that involve complex heuristic designs, we present a simple yet effective solution by employing instance-aware dynamic networks.

47, TITLE: Looking Twice for Partial Clues: Weakly-supervised Part-Mentored Attention Network for Vehicle Re-Identification
AUTHORS: Lisha Tang ; Yi Wang ; Lap-Pui Chau
CATEGORY: cs.CV [cs.CV]
HIGHLIGHT: In this paper, we propose a weakly supervised Part-Mentored Attention Network (PMANet) composed of a Part Attention Network (PANet) for vehicle part localization with self-attention and a Part-Mentored Network (PMNet) for mentoring the global and local feature aggregation.

48, TITLE: Synthesizing Human Faces Using Latent Space Factorization and Local Weights (Extended Version)
AUTHORS: Minyoung Kim ; Young J. Kim
CATEGORY: cs.GR [cs.GR, cs.CV]
HIGHLIGHT: We propose a 3D face generative model with local weights to increase the model's variations and expressiveness.

49, TITLE: An Experimental Study of Data Heterogeneity in Federated Learning Methods for Medical Imaging
AUTHORS: Liangqiong Qu ; Niranjan Balachandar ; Daniel L Rubin
CATEGORY: cs.LG [cs.LG, cs.AI, cs.CV]
HIGHLIGHT: In this paper, we investigate the deleterious impact of a taxonomy of data heterogeneity regimes on federated learning methods, including quantity skew, label distribution skew, and imaging acquisition skew.

50, TITLE: Know Thyself: Transferable Visuomotor Control Through Robot-Awareness
AUTHORS: Edward S. Hu ; Kun Huang ; Oleh Rybkin ; Dinesh Jayaraman
CATEGORY: cs.LG [cs.LG, cs.CV, cs.RO]
HIGHLIGHT: We propose a "robot-aware" solution paradigm that exploits readily available robot "self-knowledge" such as proprioception, kinematics, and camera calibration to achieve this.

51, TITLE: Path Integrals for The Attribution of Model Uncertainties
AUTHORS: Iker Perez ; Piotr Skalski ; Alec Barns-Graham ; Jason Wong ; David Sutton
CATEGORY: cs.LG [cs.LG, cs.CV, stat.ML]
HIGHLIGHT: In this paper, we leverage path integrals to attribute uncertainties in Bayesian differentiable models.

52, TITLE: A Stepped Sampling Method for Video Detection Using LSTM
AUTHORS: Dengshan Li ; Rujing Wang ; Chengjun Xie
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: From the perspective of simulating human memory method, we propose a stepped sampler based on the "repeated input".

53, TITLE: Self Training with Ensemble of Teacher Models
AUTHORS: Soumyadeep Ghosh ; Sanjay Kumar ; Janu Verma ; Awanish Kumar
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: Recent progress of self-training based approaches have shown promise in this area, which leads to this study where we utilize an ensemble approach for the same.

54, TITLE: Visual Representation Learning Does Not Generalize Strongly Within The Same Domain
AUTHORS: LUKAS SCHOTT et. al.
CATEGORY: cs.LG [cs.LG, cs.CV]
HIGHLIGHT: In this paper, we test whether 17 unsupervised, weakly supervised, and fully supervised representation learning approaches correctly infer the generative factors of variation in simple datasets (dSprites, Shapes3D, MPI3D).

55, TITLE: Detection of Double Compression in MPEG-4 Videos Using Refined Features-based CNN
AUTHORS: Seung-Hun Nam ; Wonhyuk Ahn ; Myung-Joon Kwon ; In-Jae Yu
CATEGORY: cs.MM [cs.MM, cs.AI, cs.CV]
HIGHLIGHT: This Letter presents a convolutional neural network for detecting double compression in MPEG-4 videos.

56, TITLE: Playful Interactions for Representation Learning
AUTHORS: Sarah Young ; Jyothish Pari ; Pieter Abbeel ; Lerrel Pinto
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this work, we propose to use playful interactions in a self-supervised manner to learn visual representations for downstream tasks.

57, TITLE: Autonomy 2.0: Why Is Self-driving Always 5 Years Away?
AUTHORS: Ashesh Jain ; Luca Del Pero ; Hugo Grimmett ; Peter Ondruska
CATEGORY: cs.RO [cs.RO, cs.AI, cs.CV, cs.LG]
HIGHLIGHT: In this paper, we study the history, composition, and development bottlenecks of the modern self-driving stack.

58, TITLE: Automatic and Explainable Grading of Meningiomas from Histopathology Images
AUTHORS: JONATHAN GANZ et. al.
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG, 68T99]
HIGHLIGHT: In this work, we present and compare three approaches towards fully automatic meningioma grading from histology whole slide images.

59, TITLE: Frequency-Supervised MR-to-CT Image Synthesis
AUTHORS: Zenglin Shi ; Pascal Mettes ; Guoyan Zheng ; Cees Snoek
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we find that all existing approaches share a common limitation: reconstruction breaks down in and around the high-frequency parts of CT images.

60, TITLE: Adversarial Continual Learning for Multi-Domain Hippocampal Segmentation
AUTHORS: Marius Memmel ; Camila Gonzalez ; Anirban Mukhopadhyay
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: We propose an architecture that leverages the simultaneous availability of two or more datasets to learn a disentanglement between the content and domain in an adversarial fashion.

61, TITLE: Improving Interpretability of Deep Neural Networks in Medical Diagnosis By Investigating The Individual Units
AUTHORS: Woo-Jeoung Nam ; Seong-Whan Lee
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we demonstrate the efficiency of recent attribution techniques to explain the diagnostic decision by visualizing the significant factors in the input image.

62, TITLE: ANFIC: Image Compression Using Augmented Normalizing Flows
AUTHORS: Yung-Han Ho ; Chih-Chun Chan ; Wen-Hsiao Peng ; Hsueh-Ming Hang ; Marek Domanski
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF).

63, TITLE: Attention-based Multi-scale Gated Recurrent Encoder with Novel Correlation Loss for COVID-19 Progression Prediction
AUTHORS: AISHIK KONWER et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We present a deep learning-based approach to predict lung infiltrate progression from serial chest radiographs (CXRs) of COVID-19 patients.

64, TITLE: Input Agnostic Deep Learning for Alzheimer's Disease Classification Using Multimodal MRI Images
AUTHORS: Aidana Massalimova ; Huseyin Atakan Varol
CATEGORY: eess.IV [eess.IV, cs.CV, cs.LG]
HIGHLIGHT: In this work, we utilize a multi-modal deep learning approach in classifying normal cognition, mild cognitive impairment and AD classes on the basis of structural MRI and diffusion tensor imaging (DTI) scans from the OASIS-3 dataset.

65, TITLE: Fully Polarimetric SAR and Single-Polarization SAR Image Fusion Network
AUTHORS: LIUPENG LIN et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: To take advantage of the polarimetric information of the low-resolution PolSAR (LR-PolSAR) image and the spatial information of the high-resolution single-polarization SAR (HR-SinSAR) image, we propose a fusion framework for joint LR-PolSAR image and HR-SinSAR image and design a cross-attention mechanism to extract features from the joint input data.

66, TITLE: Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures
AUTHORS: HOLGER R. ROTH et. al.
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this work, we combine FL with an AutoML technique based on local neural architecture search by training a "supernet".

67, TITLE: Real-Time Mapping of Tissue Properties for Magnetic Resonance Fingerprinting
AUTHORS: Yilin Liu ; Yong Chen ; Pew-Thian Yap
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: In this paper, we introduce a novel end-to-end deep learning framework to seamlessly map the tissue properties directly from spiral k-space MRF data, thereby avoiding time-consuming processing such as the nonuniform fast Fourier transform (NUFFT) and the dictionary-based Fingerprint matching.

68, TITLE: Zero-Shot Domain Adaptation in CT Segmentation By Filtered Back Projection Augmentation
AUTHORS: Talgat Saparov ; Anvar Kurmukov ; Boris Shirokih ; Mikhail Belyaev
CATEGORY: eess.IV [eess.IV, cs.CV]
HIGHLIGHT: We propose Filtered Back-Projection Augmentation (FBPAug), a simple and surprisingly efficient approach to augment CT images in sinogram space emulating reconstruction with different kernels.

计算机视觉论文-2021-07-20相关推荐

GMOJ - 2021.07.20【普及组】模拟赛C组 - 排座椅(seat)、传球游戏(ball)、立体图(drawing)、间谍派遣、seek
文章目录 luogu博客链接 GMOJ - 2021.07.20[普及组]模拟赛C组 - 排座椅(seat).传球游戏(ball).立体图(drawing).间谍派遣.seek T1 排座椅(seat ...
【AI视野·今日CV 计算机视觉论文速览第202期】Thu, 20 May 2021
AI视野·今日CS.CV 计算机视觉论文速览 Thu, 20 May 2021 Totally 47 papers
2021年必读的10 个计算机视觉论文总结
点击上方"3D视觉工坊",选择"星标" 干货第一时间送达作者丨Louis Bouchard 来源丨DeepHub IMBA 编辑丨极市平台本文是作者总结的今 ...
【AI视野·今日CV 计算机视觉论文速览第240期】Thu, 4 Nov 2021
AI视野·今日CS.CV 计算机视觉论文速览 Thu, 4 Nov 2021 Totally 35 papers
【AI视野·今日CV 计算机视觉论文速览第239期】Wed, 3 Nov 2021
AI视野·今日CS.CV 计算机视觉论文速览 Wed, 3 Nov 2021 Totally 48 papers
【AI视野·今日CV 计算机视觉论文速览第238期】Fri, 1 Oct 2021
AI视野·今日CS.CV 计算机视觉论文速览 Fri, 1 Oct 2021 Totally 62 papers
【AI视野·今日CV 计算机视觉论文速览第237期】Thu, 30 Sep 2021
AI视野·今日CS.CV 计算机视觉论文速览 Thu, 30 Sep 2021 Totally 47 papers
【AI视野·今日CV 计算机视觉论文速览第233期】Tue, 3 Aug 2021
AI视野·今日CS.CV 计算机视觉论文速览 Tue, 3 Aug 2021 Totally xx papers
【AI视野·今日CV 计算机视觉论文速览第232期】Thu, 8 Jul 2021
AI视野·今日CS.CV 计算机视觉论文速览 Thu, 8 Jul 2021 Totally 62 papers
【AI视野·今日CV 计算机视觉论文速览第229期】Thu, 1 Jul 2021
AI视野·今日CS.CV 计算机视觉论文速览 Thu, 1 Jul 2021 Totally 53 papers

计算机视觉论文-2021-07-20

计算机视觉论文-2021-07-20相关推荐

最新文章

热门文章