https://github.com/52cv/cvprw-2021-papers

Last synced: 4 months ago
JSON representation
Host: GitHub
URL: https://github.com/52cv/cvprw-2021-papers
Owner: 52CV
Created: 2021-04-19T08:33:07.000Z (about 5 years ago)
Default Branch: main
Last Pushed: 2021-06-08T02:04:28.000Z (about 5 years ago)
Last Synced: 2025-11-16T15:22:22.928Z (8 months ago)
Size: 216 KB
Stars: 12
Watchers: 2
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md
Awesome Lists containing this project

README

          # CVPR2021 Workshop 组会最新论文/代码(持续更新)

## :star2:[CVPR2021最新信息及已接收论文/代码(持续更新)](https://github.com/52CV/CVPR-2021-Papers)

### :fireworks::fireworks::fireworks:更新提示：6月8日新增2篇

* [Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization](https://arxiv.org/abs/2106.03088)

* 元学习

  * [DAMSL: Domain Agnostic Meta Score-based Learning](https://arxiv.org/abs/2106.03041)

### :fireworks::fireworks::fireworks:更新提示：6月7日新增1篇

* 细粒度

  * [Fine-Grained Visual Classification of Plant Species In The Wild: Object Detection as A Reinforced Means of Attention](https://arxiv.org/abs/2106.02141)

### :fireworks::fireworks::fireworks:更新提示：6月4日新增2篇

* Transformer

  * [Anticipative Video Transformer](https://arxiv.org/abs/2106.02036)
:house:[project](https://facebookresearch.github.io/AVT/)
在 CVPR 21 EPIC-Kitchens 行动预期挑战排行榜上排名第一

* 图像处理

  * [NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results](https://arxiv.org/abs/2106.01439)

### :fireworks::fireworks::fireworks:更新提示：6月3日新增3篇

* 半监督

  * [The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop](https://arxiv.org/abs/2106.01364)

* 分割

  * [Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation](https://arxiv.org/abs/2106.01061)

* 细粒度

  * [Cleaning and Structuring the Label Space of the iMet Collection 2020](https://arxiv.org/abs/2106.00815)
:star:[code](https://github.com/sunniesuhyoung/iMet2020cleaned)

### :fireworks::fireworks::fireworks:更新提示：6月2日新增3篇

* 语义分割

  * [Detecting Anomalies in Semantic Segmentation with Prototypes](https://arxiv.org/abs/2106.00472)

* 未分

  * [PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes](https://arxiv.org/abs/2106.00446)

  * [Semi-Supervised Disparity Estimation with Deep Feature Reconstruction](https://arxiv.org/abs/2106.00318)

### :fireworks::fireworks::fireworks:更新提示：6月1日新增3篇

* 车辆

  * [Connecting Language and Vision for Natural Language-Based Vehicle Retrieval](https://arxiv.org/abs/2105.14897)
:star:[code](https://github.com/ShuaiBai623/AIC2021-T5-CLV)

* 目标检测

  * [Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner](https://arxiv.org/abs/2105.14693)
:star:[code](https://github.com/2-Chae/A-NDFT)
本文所介绍算法 A-NDFT，是对 NDFT 的改良版本。A-NDFT 利用两种加速技术，feature replay 和 slow learner。因此，在一个大规模的 UAVDT 基准上，它可以将 NDVT 的训练时间从 31 小时减少到 3 小时，同时仍然保持性能。

* 6D

  * [Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains](https://arxiv.org/abs/2105.14391)
:star:[code](https://github.com/wenbowen123/iros20-6d-pose-tracking)

### :fireworks::fireworks::fireworks:更新提示：5月31日新增1篇

* [The Herbarium 2021 Half–Earth Challenge Dataset](https://arxiv.org/abs/2105.13808)

### :fireworks::fireworks::fireworks:更新提示：5月28日新增1篇

* [RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection](https://arxiv.org/abs/2105.12789)

### :fireworks::fireworks::fireworks:更新提示：5月27日新增1篇

* 计算成像

  * [How to Calibrate Your Event Camera](https://arxiv.org/abs/2105.12362)
:star:[code](https://github.com/uzh-rpg/e2calib)

### :fireworks::fireworks::fireworks:更新提示：5月26日新增1篇

* 三维

  * [Real-time Monocular Depth Estimation with Sparse Supervision on Mobile](https://arxiv.org/abs/2105.12053)

|:cat:|:dog:|:mouse:|:hamster:|:tiger:|

|------|------|------|------|------|

|[38.Transformer](#38)|[37.6D](#37)|[36.OCR](#36)|

|[35.Data Augmentation(数据增广)](#35)|[34.Computational Photography(光学、几何、光场成像、计算摄影)](#34)|[33.GAN](#33)|[32.手语识别](#32)|[31.图像分类](#31)|

|[30.目标跟踪](#30)|[29.Auto-ML&NAS](#29)|[28.医学影像](#28)|[27.人体姿态估计](#27)|[26.无监督](#26)|

|[25.SLAM/AR/VR/机器人](#25)|[24.模型压缩&应用部署](#24)|[23.人脸](#23)|[22.重建](#22)|[21.视频](#21)|

|[20.三维](#20)|[19.光流](#19)|[18.图像检索](#18)|[17.动作检测识别](#17)|[16.人员重识别](#16)|

|[15.遥感航空影像](#15)|[14VQA](#14)|[13.SR](#13)|[12.图像分割](#12)|[11.图像处理](#11)|

|[10.目标检测](#10)|[9.姿态估计](#9)|[8.Camera Trap Images-相机陷阱图像](#8)|[7.图像到图像翻译](#7)|[6.手绘草图](#6)|

|[5.车辆车牌与智能驾驶](#5)|[4.数据集](#4)|[3.各种神经网络](#3)|[2.算法学习](#2)|[1.Unkown(未分)](#1)|



## 38.Transformer

  * [Anticipative Video Transformer](https://arxiv.org/abs/2106.02036)
:house:[project](https://facebookresearch.github.io/AVT/)
在 CVPR 21 EPIC-Kitchens 行动预期挑战排行榜上排名第一



## 37.6D

  * [Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains](https://arxiv.org/abs/2105.14391)
:star:[code](https://github.com/wenbowen123/iros20-6d-pose-tracking)



## 36.OCR

* 场景文本识别

  * [RSCA: Real-time Segmentation-based Context-Aware Scene Text Detection](https://arxiv.org/abs/2105.12789)



## 35.Data Augmentation(数据增广)

  * [Wisdom for the Crowd: Discoursive Power in Annotation Instructions for Computer Vision](https://arxiv.org/abs/2105.10990)



## 34.Computational Photography(光学、几何、光场成像、计算摄影)

* [How to Calibrate Your Event Camera](https://arxiv.org/abs/2105.12362)
:star:[code](https://github.com/uzh-rpg/e2calib)

* HDR 成像

  * [ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging](https://arxiv.org/abs/2105.10697)
:star:[code](https://github.com/Pea-Shooter/ADNet)

  



## 33.GAN

* [Learning to Generate Novel Scene Compositions from Single Images and Videos](https://arxiv.org/abs/2105.05847)

* [Directional GAN: A Novel Conditioning Strategy for Generative Networks](https://arxiv.org/abs/2105.05712)



## 32.手语识别

* [ChaLearn LAP Large Scale Signer Independent Isolated Sign Language Recognition Challenge: Design, Results and Future Research](https://arxiv.org/abs/2105.05066)



## 31.图像分类

  * [Boosting Co-teaching with Compression Regularization for Label Noise](https://arxiv.org/abs/2104.13766)
:star:[code](https://github.com/yingyichen-cyy/Nested-Co-teaching)

* 多标签分类

  * [PLM: Partial Label Masking for Imbalanced Multi-label Classification](https://arxiv.org/abs/2105.10782)

* 细粒度

  * [Cleaning and Structuring the Label Space of the iMet Collection 2020](https://arxiv.org/abs/2106.00815)
:star:[code](https://github.com/sunniesuhyoung/iMet2020cleaned)

  * [Fine-Grained Visual Classification of Plant Species In The Wild: Object Detection as A Reinforced Means of Attention](https://arxiv.org/abs/2106.02141)



## 30.目标跟踪

* [Detecting and Matching Related Objects with One Proposal Multiple Predictions](https://arxiv.org/abs/2104.12574)

* [Differentiable Event Stream Simulator for Non-Rigid 3D Tracking](https://arxiv.org/abs/2104.15139)
:house:[project](http://gvv.mpi-inf.mpg.de/projects/Event-based_Non-rigid_3D_Tracking/)

* [City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones](https://arxiv.org/abs/2105.06623)
:star:[code](https://github.com/LCFractal/AIC21-MTMC)



## 29.Auto-ML&NAS

* Auto-ML

  * [Network Space Search for Pareto-Efficient Spaces](https://arxiv.org/abs/2104.11014)



## 28.Medical Imaging医学影像

* [GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review](https://arxiv.org/abs/2104.10603)

* 医学图像识别

  * [Can self-training identify suspicious ugly duckling lesions?](https://arxiv.org/abs/2105.07116)

* 无监督检测

  * [Unsupervised Detection of Cancerous Regions in Histology Imagery using Image-to-Image Translation](https://arxiv.org/abs/2104.13786)



## 27.人体姿态估计

  * [Table Tennis Stroke Recognition Using Two-Dimensional Human Pose Estimation](https://arxiv.org/abs/2104.09907)



## 26.无监督/半监督

* 无监督

  * [Perceptual Loss for Robust Unsupervised Homography Estimation](https://arxiv.org/abs/2104.10011)

* 半监督

  * [The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop](https://arxiv.org/abs/2106.01364)



## 25.SLAM/AR/VR/机器人

  * [Comparing Representations in Tracking for Event Camera-based SLAM](https://arxiv.org/abs/2104.09887)
:star:[code](https://github.com/gogojjh/ESVO_extension)



## 24.Quantization/Pruning/Knowledge Distillation/Model Compression(量化、剪枝、蒸馏、模型压缩/扩展与优化)

* [BasisNet: Two-stage Model Synthesis for Efficient Inference](https://arxiv.org/abs/2105.03014)

* 知识蒸馏

  * [Distill on the Go: Online knowledge distillation in self-supervised learning](https://arxiv.org/abs/2104.09866)

* 量化

  * [Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics](https://arxiv.org/abs/2104.11849)

  * [Pareto-Optimal Quantized ResNet Is Mostly 4-bit](https://arxiv.org/abs/2105.03536)
:star:[code](https://github.com/google-research/google-research/tree/master/aqt)



## 23.Face人脸

* 人脸表情识别

  * [I Only Have Eyes for You: The Impact of Masks On Convolutional-Based Facial Expression Recognition](https://arxiv.org/abs/2104.08353)

* 人脸识别

  * [EQFace: A Simple Explicit Quality Network for Face Recognition](https://arxiv.org/abs/2105.00634)
:star:[code](https://github.com/deepcam-cn/facequality)



## 22.Reconstruction重建

* 3D 人体重建

  * [Temporal Consistency Loss for High Resolution Textured and Clothed 3DHuman Reconstruction from Monocular Video](https://arxiv.org/abs/2104.09259)



## 21.Video视频

* 视频恢复

  * [Restoration of Video Frames from a Single Blurred Image with Motion Understanding](https://arxiv.org/abs/2104.09134)

* 异常检测

  * [An Efficient Approach for Anomaly Detection in Traffic Videos](https://arxiv.org/abs/2104.09758)

  * [Good Practices and A Strong Baseline for Traffic Anomaly Detection](https://arxiv.org/abs/2105.03827)
在 CVPR 2021 NVIDIA AI CITY 挑战赛中的 Traffic Anomaly Detection(交通异常检测)中排名第一

* 风格迁移

  * [Automatic Non-Linear Video Editing Transfer](https://arxiv.org/abs/2105.06988)



## 20.3D三维

* [OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas](https://arxiv.org/abs/2104.09403)
:star:[code](https://github.com/rshivansh/OmniLayout)

* 深度估计

  * [Real-time Monocular Depth Estimation with Sparse Supervision on Mobile](https://arxiv.org/abs/2105.12053)



## 19.Optical Flow光流

* [OmniFlow: Human Omnidirectional Optical Flow](https://arxiv.org/abs/2104.07960)
:sunflower:[dataset](https://www.tu-chemnitz.de/etit/dst/forschung/comp_vision/datasets/omniflow/)



## 18.Image Retrieval图像检索

* [Continual learning in cross-modal retrieval](https://arxiv.org/abs/2104.06806)



## 17.Action Detection and Recognition动作检测识别

* action spotting-重点动作识别

  * [Temporally-Aware Feature Pooling for Action Spotting in Soccer Broadcasts](https://arxiv.org/abs/2104.06779)

  * [Camera Calibration and Player Localization in SoccerNet-v2 and Investigation of their Representations for Action Spotting](https://arxiv.org/abs/2104.09333)
:sunflower:[dataset](https://soccer-net.org/)

* 动作检测

  * [Three-stream network for enriched Action Recognition](https://arxiv.org/abs/2104.13051)



## 16.Person Re-Identifications人员重识别

* [Graph-based Person Signature for Person Re-Identifications](https://arxiv.org/abs/2104.06770)

* 行人检测

  * [Generalizable Multi-Camera 3D Pedestrian Detection](https://arxiv.org/abs/2104.05813)

* 基于视频的 Reid

  * [Video-based Person Re-identification without Bells and Whistles](https://arxiv.org/abs/2105.10678)
:star:[code](https://github.com/jackie840129/CF-AAN)



## 15.Aeria/Drones/Satellite/RS Image(航空影像/无人机)

* 三维重建

  * [Machine-learned 3D Building Vectorization from Satellite Imagery](https://arxiv.org/abs/2104.06485)



## 14VQA-视觉问答

* [Dealing with Missing Modalities in the Visual Question Answer-Difference Prediction Task through Knowledge Distillation](https://arxiv.org/abs/2104.05965)



## 13.SR-超分辨率

* 视频超分辨率

  * [Efficient Space-time Video Super Resolution using Low-Resolution Flow and Mask Upsampling](https://arxiv.org/abs/2104.05778)

  * [NTIRE 2021 Challenge on Video Super-Resolution](https://arxiv.org/abs/2104.14852)
:house:[project](https://data.vision.ee.ethz.ch/cvl/ntire21/)

* 图像超分辨率

  * [Anchor-based Plain Net for Mobile Image Super-Resolution](https://arxiv.org/abs/2105.09750)
:star:[code](https://github.com/NJU-Jet/SR_Mobile_Quantization)



## 12.Image Segmentation图像分割

* 语义分割

  * [Improving Online Performance Prediction for Semantic Segmentation](https://arxiv.org/abs/2104.05255) 

  * [Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation](https://arxiv.org/abs/2104.09254)

  * [Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation](https://arxiv.org/abs/2104.14203)

  * [Detecting Anomalies in Semantic Segmentation with Prototypes](https://arxiv.org/abs/2106.00472)

* 实例分割

  * [Fashion-Guided Adversarial Attack on Person Segmentation](https://arxiv.org/abs/2104.08422)

* 视频目标分割

  * [Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation](https://arxiv.org/abs/2106.01061)



## 11.Image Processing图像处理

* [NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results](https://arxiv.org/abs/2106.01439)

* 去除滤镜

  * [Instagram Filter Removal on Fashionable Images](https://arxiv.org/abs/2104.05072)

* 去雾

  * [A Two-branch Neural Network for Non-homogeneous Dehazing via Ensemble Learning](https://arxiv.org/abs/2104.08902)
:star:[code](https://github.com/liuh127/Two-branch-dehazing)

* 图像压缩

  * [DANICE: Domain adaptation without forgetting in neural image compression](https://arxiv.org/abs/2104.09370) 

* 图像质量评估

  * [Region-Adaptive Deformable Network for Image Quality Assessment](https://arxiv.org/abs/2104.11599)
:star:[code](https://github.com/IIGROUP/RADN)

  * [Perceptual Image Quality Assessment with Transformers](https://arxiv.org/abs/2104.14730)
:star:[code](https://github.com/manricheon/IQT)
在NTIRE 2021年感知IQA挑战中获得第一名

* 去雨

  * [Multi-Scale Hourglass Hierarchical Fusion Network for Single Image Deraining](https://arxiv.org/abs/2104.12100)

* 照片补光

  * [NTIRE 2021 Depth Guided Image Relighting Challenge](https://arxiv.org/abs/2104.13365)
:star:[code](https://github.com/majedelhelou/VIDIT)

* 去模糊

  * [NTIRE 2021 Challenge on Image Deblurring](https://arxiv.org/abs/2104.14854)
:house:[project](https://data.vision.ee.ethz.ch/cvl/ntire21/)

* 图像补光

  * [Multi-modal Bifurcated Network for Depth Guided Image Relighting](https://arxiv.org/abs/2105.00690)
:star:[code](https://github.com/weitingchen83/NTIRE2021-Depth-   Guided-Image-Relighting-MBNet)
是 NTIRE 2021 深度指南一对一补光挑战赛的冠军

  * [S3Net: A Single Stream Structure for Depth Guided Image Relighting](https://arxiv.org/abs/2105.00681)
:star:[code](https://github.com/dectrfov/NTIRE-2021-Depth-Guided-Image-Any-to-Any-relighting)
在 NTIRE 2021 深度引导的任意重新照明挑战中获得第3名

  * [Physically Inspired Dense Fusion Networks for Relighting](https://arxiv.org/abs/2105.02209)
 OIDDR-Net排名第二，AMIDR-Net 在 NTIRE 2021 年深度引导图像重光挑战中名列前五名

* 图像恢复

  * [EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration](https://arxiv.org/abs/2105.04872)
:star:[code](https://github.com/zeyuxiao1997/EDPN)

* bokeh effect(背景虚化)

  * [Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image](https://arxiv.org/abs/2105.07174)
:star:[code](https://github.com/saikatdutta/Stacked_DMSHN_bokeh)



## 10.Object Detection目标检测

* [LSPnet: A 2D Localization-oriented Spacecraft Pose Estimation Neural Network](https://arxiv.org/abs/2104.09248)

* [Pseudo-IoU: Improving Label Assignment in Anchor-Free Object Detection](https://arxiv.org/abs/2104.14082)
:star:[code](https://github.com/SHI-Labs/Pseudo-IoU-for-Anchor-Free-Object-Detection)

* [Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner](https://arxiv.org/abs/2105.14693)
:star:[code](https://github.com/2-Chae/A-NDFT)
本文所介绍算法 A-NDFT，是对 NDFT 的改良版本。A-NDFT 利用两种加速技术，feature replay 和 slow learner。因此，在一个大规模的 UAVDT 基准上，它可以将 NDVT 的训练时间从 31 小时减少到 3 小时，同时仍然保持性能。

* 3D目标检测

  * [High-level camera-LiDAR fusion for 3D object detection with machine learning](https://arxiv.org/abs/2105.11060)



## 9.Pose Estimation姿态估计

* [Towards Automated and Marker-less Parkinson Disease Assessment: Predicting UPDRS Scores using Sit-stand videos](https://arxiv.org/abs/2104.04650)



## 8.Camera Trap Images-相机陷阱图像

* [Filtering Empty Camera Trap Images in Embedded Systems](https://arxiv.org/abs/2104.08859)
:star:[code](https://github.com/alcunha/filtering-empty-camera-trap-images)



## 7.Image-to-Image Translation图像到图像翻译

* [Dual Contrastive Learning for Unsupervised Image-to-Image Translation](https://arxiv.org/abs/2104.07689)
:star:[code](https://github.com/JunlinHan/DCLGAN)



## 6.手绘草图

* [On Training Sketch Recognizers for New Domains](https://arxiv.org/abs/2104.08850)

* 工程草图生成

  * [Engineering Sketch Generation for Computer-Aided Design](https://arxiv.org/abs/2104.09621)



## 5.车辆车牌与智能驾驶

* 自动驾驶

  * [MVFuseNet: Improving End-to-End Object Detection and Motion Forecasting through Multi-View Fusion of LiDAR Data](https://arxiv.org/abs/2104.10772)

  * [Multi-task Learning with Attention for End-to-end Autonomous Driving](https://arxiv.org/abs/2104.10753)

  * [End-to-End Interactive Prediction and Planning with Optical Flow Distillation for Autonomous Driving](https://arxiv.org/abs/2104.08862)
:house:[project](https://sites.google.com/view/inmp-ofd)

  * [Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment](https://arxiv.org/abs/2105.05207)
:sunflower:[dataset](https://www.cruwdataset.org/)

* 车辆重识别

  * [A Strong Baseline for Vehicle Re-Identification](https://arxiv.org/abs/2104.10850)
:star:[code](https://github.com/cybercore-co-ltd/track2_aicity_2021)

  * [An Empirical Study of Vehicle Re-Identification on the AI City Challenge](https://arxiv.org/abs/2105.09701)
:star:[code](https://github.com/michuanhaohao/AICITY2021_Track2_DMT)
获得 CVPR 2021研讨会上，NVIDIA AI City Challenge（英伟达人工智能城市挑战赛）第2赛道（车辆重识别）的第一名。

* 车辆检索

  * [SBNet: Segmentation-based Network for Natural Language-based Vehicle Search](https://arxiv.org/abs/2104.11589)
:star:[code](https://github.com/lsrock1/nlp_search)

  * [Connecting Language and Vision for Natural Language-Based Vehicle Retrieval](https://arxiv.org/abs/2105.14897)
:star:[code](https://github.com/ShuaiBai623/AIC2021-T5-CLV)



## 4.Dataset数据集

* [The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions](https://arxiv.org/abs/2104.02710)

* [The iWildCam 2021 Competition Dataset](https://arxiv.org/abs/2105.03494)

* [GOO: A Dataset for Gaze Object Prediction in Retail Environments](https://arxiv.org/abs/2105.10793)
:sunflower:[dataset](https://github.com/upeee/GOO-GAZE2021)

* [The Herbarium 2021 Half–Earth Challenge Dataset](https://arxiv.org/abs/2105.13808)



## 3.各种神经网络

* CNN

  * [AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks](https://arxiv.org/abs/2104.07770)
:star:[code](https://github.com/Spark001/AsymmNet)

* DNN

  * [Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks](https://arxiv.org/abs/2104.07085)     

* BNN-二进制神经网络

  * [A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks](https://arxiv.org/abs/2104.05124)



## 2.算法学习

* 主动学习

  * [A Mathematical Analysis of Learning Loss for Active Learning in Regression](https://arxiv.org/abs/2104.09315)

* 对比学习

  * [Contrastive Learning Improves Model Robustness Under Label Noise](https://arxiv.org/abs/2104.08984)

* 类增量学习

  * [Class-Incremental Learning with Generative Classifiers](https://arxiv.org/abs/2104.10093)
:star:[code](https://github.com/GMvandeVen/class-incremental-learning)

* 增量学习

  * [IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay](https://arxiv.org/abs/2104.10588)

* 持续学习

  * [Class-Incremental Experience Replay for Continual Learning under Concept Drift](https://arxiv.org/abs/2104.11861)

* 联邦学习

  * [Towards Fair Federated Learning with Zero-Shot Data Augmentation](https://arxiv.org/abs/2104.13417)

  * [Cluster-driven Graph Federated Learning over Multiple Domains](https://arxiv.org/abs/2104.14628)

* 元学习

  * [DAMSL: Domain Agnostic Meta Score-based Learning](https://arxiv.org/abs/2106.03041)



## 1.Unkown未分

* [Reconsidering CO2 emissions from Computer Vision](https://arxiv.org/abs/2104.08702)

* [Assessment of deep learning based blood pressure prediction from PPG and rPPG signals](https://arxiv.org/abs/2104.09313)

* [I Find Your Lack of Uncertainty in Computer Vision Disturbing](https://arxiv.org/abs/2104.08188)

* [Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis](https://arxiv.org/abs/2104.10252)

* [Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities](https://arxiv.org/abs/2104.11691)

* [The 5th AI City Challenge](https://arxiv.org/abs/2104.12233)

* [Width Transfer: On the (In)variance of Width Optimization](https://arxiv.org/abs/2104.13255)

* [Sign Segmentation with Changepoint-Modulated Pseudo-Labelling](https://arxiv.org/abs/2104.13817)

* [CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications](https://arxiv.org/abs/2104.14126)

* [Feedback control of event cameras](https://arxiv.org/abs/2105.00409)

* [Effectively Leveraging Attributes for Visual Similarity](https://arxiv.org/abs/2105.01695)

* [Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms](https://arxiv.org/abs/2105.03596)
与最先进的技术相比，在Jetson Xavier NX 上使用 ImageNet 的实验结果表明，在相似的 ImageNet Top-1 精度下，该方法的速度最高可达 3.5倍（CPU），2.4倍（GPU），或者在相似的延迟下，精度更高 3.8%（CPU），5.1%（GPU）。

* [High-Resolution Complex Scene Synthesis with Transformers](https://arxiv.org/pdf/2105.06458.pdf)

* [Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example](https://arxiv.org/abs/2105.06407)

* [Texture Generation with Neural Cellular Automata](https://arxiv.org/abs/2105.07299)
:house:[project](https://selforglive.github.io/cvpr_textures/)

* [Single View Geocentric Pose in the Wild](https://arxiv.org/abs/2105.08229)
:star:[code](https://github.com/pubgeo/monocular-geocentric-pose)

* [PAL: Intelligence Augmentation using Egocentric Visual Context Detection](https://arxiv.org/abs/2105.10735)

* [PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes](https://arxiv.org/abs/2106.00446)

* [Semi-Supervised Disparity Estimation with Deep Feature Reconstruction](https://arxiv.org/abs/2106.00318)

* [Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization](https://arxiv.org/abs/2106.03088)

* 异常检测

  * [Brittle Features May Help Anomaly Detection](https://arxiv.org/abs/2104.10453)
ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

https://github.com/52cv/cvprw-2021-papers

Awesome Lists containing this project

README
