TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting，CVPR 2022 Oral

论文：https://arxiv.org/abs/2204.01018 [2204.01018] TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting (arxiv.org)

Code: https://github.com/SvipRepetitionCounting/TransRAC GitHub - SvipRepetitionCounting/TransRAC: (CVPR 2022 Oral) Official implementation: TransRAC Dataset: https://svip-lab.github.io/dataset/RepCount_dataset.html

Shanghaitech Vision and Intelligent Perception(SVIP) LAB (svip-lab.github.io)

Learning Part Segmentation through Unsupervised Domain Adaptation from Synthetic Vehicles，CVPR 2022 Oral

Paper: https://arxiv.org/abs/2103.14098

Code: GitHub - qliu24/render-3d-segmentation

数据：UDA-Part: A Part Segmentation Dataset Based on 3D Computer Graphics Models | UDA-Part

Semantic-Aware Domain Generalized Segmentation，CVPR 2022 Oral

Paper: [2204.00822] Semantic-Aware Domain Generalized Segmentation (arxiv.org)
Code:

GitHub - leolyj/SAN-SAW: This is the code related to "Semantic-Aware Domain Generalized Segmentation" (CVPR 2022)

MAXIM: Multi-Axis MLP for Image Processing，CVPR 2022 Oral

Paper: [2201.02973] MAXIM: Multi-Axis MLP for Image Processing (arxiv.org)
Code: https://github.com/google-research/maxim

Correlation Verification for Image Retrieval，CVPR 2022 Oral

论文：[2204.01458] Correlation Verification for Image Retrieval (arxiv.org)
代码：GitHub - sungonce/CVNet: Official PyTorch Implementation of Correlation Verifcation for Image Retrieval, CVPR 2022 (Oral Presentation)

Rethinking Semantic Segmentation: A Prototype View，CVPR 2022 Oral

论文：[2203.15102] Rethinking Semantic Segmentation: A Prototype View (arxiv.org)
代码：GitHub - tfzhou/ProtoSeg: CVPR2022 (Oral) - Rethinking Semantic Segmentation: A Prototype View

Dual-AI: Dual-path Action Interaction Learning for Group Activity Recognition，CVPR 2022 Oral

论文：[2204.02148] Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition (arxiv.org)
代码：Dual-AI: Dual-path Actor Interaction Learning for Group Activity Recognition (mingfei.info)

GAN-Supervised Dense Visual Alignment，CVPR 2022 Oral

Paper: [2112.05143] GAN-Supervised Dense Visual Alignment (arxiv.org)
Code: https://github.com/wpeebles/gangealing
Project: GAN-Supervised Dense Visual Alignment (wpeebles.com)

Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry，CVPR 2022 Oral

论文：[2112.08177] Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry (arxiv.org)
代码：GitHub - baegwangbin/MaGNet: (CVPR 2022 - oral) Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry

SeqFormer：Sequential Transformer for Video Instance Segmentation, ECCV 2022 Oral

SeqFormer：https://arxiv.org/abs/2112.08275

IDOL：https://arxiv.org/abs/2207.10661

Official code address: https://github.com/wjf5203/VNex

ECCV 2022 Oral | Full Score Paper! Video instance segmentation new SOTA: SeqFormer & IDOL - zhihu.com

In Defense of Online Models for Video Instance Segmentation, ECCV 2022 Oral

In Defense of Online Models for Video Instance Segmentation - 知乎 (zhihu.com)

https://arxiv.org/abs/2207.10661

Large-scale Unsupervised Semantic Segmentation，TPAMI2022

Dataset download: github.com/LUSSeg/ImageNet-S

Mainstream method code: github.com/LUSSeg/ImageNetSegModel

The method proposed in the paper: github.com/LUSSeg/PASS

Paper address: arxiv.org/pdf/2106.03149.pdf

TPAMI2022: Large-scale Unsupervised Semantic Segmentation (LUSS) and its dataset Image-S

Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation

Paper address: https://arxiv.org/pdf/2206.06363.pdf

Open source code: https://github.com/wvangansbeke/MaskDistill

Unsupervised Semantic Segmentation-MaskDistill: Use Transformer to mine priors, no need for any labeled data to reach SOTA

StructToken : Rethinking Semantic Segmentation with Structural Prior

https://arxiv.org/pdf/2203.12612.pdf

A New Paradigm for Semantic Segmentation: Shanghai AI Lab, Beiyou and SenseTime jointly proposed StructToken

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers，ECCV 2022

Paper address: https://arxiv.org/abs/2207.08409 [1]

Code address: https://github.com/Sense-X/TokenMix [2]

ECCV 2022 hangs MixUp and CutMix! MMLab & SenseTime proposed a super data enhancement strategy "TokenMix"! - Zhihu (zhihu.com)

Shunted Self-Attention via Multi-Scale Token Aggregation

Paper address: https://arxiv.org/pdf/2111.15193.pdf

Code address: https://github.com/OliverRensu/Shunted-Transformer

CVPR2022 Oral - Shunted Transformer: New multi-scale visual Transformer backbone network

Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation

Paper address: https://arxiv.org/pdf/2203.10739.pdf

Code address: https://github.com/megvii-research/TreeEnergyLoss

CVPR2022-Tree Energy Loss: A New Method Capable of Extending Sparse Ground-truth Labels in Weakly Supervised Semantic Segmentation

Intensive reading of Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation_Griffin Valve Worker's Blog-CSDN Blog

Weakly supervised Semantic Segmentation by Pixel-to-Prototype Contrast

Paper address: https://arxiv.org/pdf/2110.07110.pdf

Code address: not open source

CVPR2022-Pixel-to-Prototype Contrast: Applying Contrastive Learning to Weakly Supervised Semantic Segmentation

Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation， CVPR2022

Paper address: https://arxiv.org/pdf/2203.00962.pdf

Code address: https://github.com/zhaozhengChen/ReCAM

CVPR2022-Class Re-Activation Maps: Class Reactivation Maps for Weakly Supervised Semantic Segmentation

Cross-Dataset Collaborative Learning for Semantic Segmentation，AAAI 2022

Paper address: https://arxiv.org/pdf/2103.11351.pdf

Code address: https://github.com/wanglixilinx/CDCL

AAAI2022-Cross-Dataset Collaborative Learning: Cross-Dataset Collaborative Learning in Semantic Segmentation

Cross-Dataset Collaborative Learning for Semantic Segmentation - 知乎

Pyraformer: Low-Complexity Pyramidal Attention for Long-range Time Series Modeling and Forecasting，ICLR 2022 oral

Paper address: https://openreview.net/pdf?id=0EXmFzUn5I
github address: https://github.com/alipay/Pyraf

ICLR 2022 Oral | Introduction to Pyraformer, an open source algorithm used by Ant Group for long-range timing modeling

Discovering and Explaining the Representation Bottleneck of DNNs，ICLR 2022 oral

The top five high-scoring papers in the ICLR 2022 Oral papers "discover and prove the bottleneck of neural network representation" (score 10,8,8,8) bazyd

Open-Set Recognition: a Good Closed-Set Classifier is All You Need?，ICLR 2022 oral

Paper link: https://arxiv.org/abs/2110.06207
Project link: https://github.com/sgvaze/osr_closed_set_all_you_need

Complement each other! Improving the accuracy of model closed-set classification can improve the accuracy of open-set detection (ICLR 2022 oral)

PICO: CONTRASTIVE LABEL DISAMBIGUATION FOR PARTIAL LABEL LEARNING， ICLR 2022 best paper

Download link: https://openreview.net/pdf?id=EhYjZy6e1gJ

This article|Industry_ICLR 2022 Best Paper Interpretation

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization，ICLR 2022 oral

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization

Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization | OpenReview

ICLR 2022 Oral: Non-Transferable Learning (anti-transfer learning) bzdww

ICLR2022oral site: zhuanlan.zhihu.com

Tsinghua University and Renmin University of China won awards, Zhejiang University was nominated, and ICLR 2022 Outstanding Paper Award was released- 知乎

reference blog

Read all the latest 20 Oral papers of CVPR 2022 in one article_Machine Learning Community Blog-CSDN Blog_cvpr oral