最新！CVPR 2021 视觉Transformer论文大盘点（43篇）
点击下方卡片，关注“CVer”公众号
AI/CV重磅干货，第一时间送达
作者：Amusi | 来源：CVer
前言
从2020下半年开始，特别是2021上半年，Visual Transformer的研究热点达到了前所未有的高峰。Amusi 认为引爆CV圈 Transformer热潮的有两篇最具代表性论文，即ECCV 2020的DETR（目标检测）和 ICLR 2021的ViT（图像分类）。
跟着DETR和ViT两篇论文的时间线，就能猜测到CVPR 2021上会涌现一大批视觉Transformer的工作。年前我还发了一个朋友圈，说会有两位数论文，结果我一统计，CVPR 2021上居然有40+篇视觉Transformer论文。
CVer 将正式盘点CVPR 2021上各个方向的工作，本篇是目前热度最高的视觉Transformer盘点，关于更多CVPR 2021的论文和开源代码，可见下面链接：
https://github.com/amusi/CVPR2021-Papers-with-Code
CVPR 2021 视觉Transformer论文（43篇）
Amusi 一共搜集了43篇Vision Transformer论文，应用涉及：图像分类、目标检测、实例分割、语义分割、行为识别、自动驾驶、关键点匹配、目标跟踪、NAS、low-level视觉、HoI、可解释性、布局生成、检索、文本检测等方向。PS：待"染指"的方向不多了...唯快不破
注1：这应该是目前各平台上最新最全面的CVPR 2021 视觉Transformer盘点资料，欢迎点赞收藏和分享
注2：目前只能检索到论文名称，所以这里只能尽量提供检索到的论文链接和代码，但不会完全，而且不提供论文单位、作者等信息（可能后续会提供完整版）。
注3：统计可能会有错误，因为很多论文原文还没有放出来，所以欢迎大家补充和提示。
1. End-to-End Human Pose and Mesh Reconstruction with Transformers
Paper: https://arxiv.org/abs/2012.09760
Code: https://github.com/microsoft/MeshTransformer
2. Temporal-Relational CrossTransformers for Few-Shot Action Recognition
Paper: https://arxiv.org/abs/2101.06184
Code: https://github.com/tobyperrett/trx
3. Kaleido-BERT：Vision-Language Pre-training on Fashion Domain
Paper: https://arxiv.org/abs/2103.16110
Code: https://github.com/mczhuge/Kaleido-BERT
4. HOTR: End-to-End Human-Object Interaction Detection with Transformers
Paper: https://arxiv.org/abs/2104.13682
Code: None
5. Multi-Modal Fusion Transformer for End-to-End Autonomous Driving
Paper: https://arxiv.org/abs/2104.09224
Code: https://github.com/autonomousvision/transfuser
6. Pose Recognition with Cascade Transformers
Paper: https://arxiv.org/abs/2104.06976
Code: https://github.com/mlpc-ucsd/PRTR
7. Variational Transformer Networks for Layout Generation
Paper: https://arxiv.org/abs/2104.02416
Code: None
8. LoFTR: Detector-Free Local Feature Matching with Transformers
Homepage: https://zju3dv.github.io/loftr/
Paper: https://arxiv.org/abs/2104.00680
Code: https://github.com/zju3dv/LoFTR
中文解读：CVPR 2021 | 稀疏纹理也能匹配？速览基于Transformers的图像特征匹配器LoFTR
9. Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Paper: https://arxiv.org/abs/2012.15840
Code: https://github.com/fudan-zvg/SETR
中文解读：CVPR 2021 | Transformer再下一城！复旦等提出SETR：语义分割网络
10. Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
Paper: https://arxiv.org/abs/2103.16553
Code: None
11. Transformer Tracking
Paper: https://arxiv.org/abs/2103.15436
Code: https://github.com/chenxin-dlut/TransT
12. HR-NAS: Searching Efficient High-Resolution Neural Architectures with Transformers
Paper(Oral): None
Code: https://github.com/dingmyu/HR-NAS
13. MIST: Multiple Instance Spatial Transformer
Paper: https://arxiv.org/abs/1811.10725
Code: None
14. Multimodal Motion Prediction with Stacked Transformers
Paper: https://arxiv.org/abs/2103.11624
Code: https://decisionforce.github.io/mmTransformer
15. Revamping cross-modal recipe retrieval with hierarchical Transformers and self-supervised learning
Paper: https://www.amazon.science/publications/revamping-cross-modal-recipe-retrieval-with-hierarchical-transformers-and-self-supervised-learning
Code: https://github.com/amzn/image-to-recipe-transformers
16. Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
Paper(Oral): https://arxiv.org/abs/2103.11681
Code: https://github.com/594422814/TransformerTrack
17. Pre-Trained Image Processing Transformer
Paper: https://arxiv.org/abs/2012.00364
Code: None
中文解读：CVPR 2021 | Transformer进军low-level视觉！北大华为等提出预训练模型IPT
18. End-to-End Video Instance Segmentation with Transformers
Paper(Oral): https://arxiv.org/abs/2011.14503
Code: https://github.com/Epiphqny/VisTR
中文解读：CVPR 2021 Oral | Transformer再突破！美团等提出VisTR：视频实例分割网络
19. UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
Paper(Oral): https://arxiv.org/abs/2011.09094
Code: https://github.com/dddzg/up-detr
中文解读：CVPR 2021 Oral | Transformer再发力！华南理工和微信提出UP-DETR：无监督预训练检测器
20. End-to-End Human Object Interaction Detection with HOI Transformer
Paper: https://arxiv.org/abs/2103.04503
Code: https://github.com/bbepoch/HoiTransformer
21. Transformer Interpretability Beyond Attention Visualization
Paper: https://arxiv.org/abs/2012.09838
Code: https://github.com/hila-chefer/Transformer-Explainability
22. Diverse Part Discovery: Occluded Person Re-Identification With Part-Aware Transformer
Paper: None
Code: None
23. LayoutTransformer: Scene Layout Generation With Conceptual and Spatial Diversity
Paper: None
Code: None
24. Line Segment Detection Using Transformers without Edges
Paper(Oral): https://arxiv.org/abs/2101.01909
Code: None
25. MaX-DeepLab: End-to-End Panoptic Segmentation With Mask Transformers
Paper: MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
Code: None
26. SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
Paper(Oral): https://arxiv.org/abs/2101.08833
Code: https://github.com/dukebw/SSTVOS
27. Facial Action Unit Detection With Transformers
Paper: None
Code: None
28. Clusformer: A Transformer Based Clustering Approach to Unsupervised Large-Scale Face and Visual Landmark Recognition
Paper: None
Code: None
29. Lesion-Aware Transformers for Diabetic Retinopathy Grading
Paper: None
Code: None
30. Topological Planning With Transformers for Vision-and-Language Navigation
Paper: https://arxiv.org/abs/2012.05292
Code: None
31. Adaptive Image Transformer for One-Shot Object Detection
Paper: None
Code: None
32. Multi-Stage Aggregated Transformer Network for Temporal Language Localization in Videos
Paper: None
Code: None
33. Taming Transformers for High-Resolution Image Synthesis
Homepage: https://compvis.github.io/taming-transformers/
Paper(Oral): https://arxiv.org/abs/2012.09841
Code: https://github.com/CompVis/taming-transformers
34. Self-Supervised Video Hashing via Bidirectional Transformers
Paper: None
Code: None
35. Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
Paper(Oral): https://hehefan.github.io/pdfs/p4transformer.pdf
Code: None
36. Gaussian Context Transformer
Paper: None
Code: None
37. General Multi-Label Image Classification With Transformers
Paper: https://arxiv.org/abs/2011.14027
Code: None
38. Bottleneck Transformers for Visual Recognition
Paper: https://arxiv.org/abs/2101.11605
Code: None
中文解读：CNN+Transformer！谷歌提出BoTNet：新主干网络！在ImageNet上达84.7%准确率！
39. VLN BERT: A Recurrent Vision-and-Language BERT for Navigation
Paper(Oral): https://arxiv.org/abs/2011.13922
Code: https://github.com/YicongHong/Recurrent-VLN-BERT
40. Less Is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
Paper(Oral): https://arxiv.org/abs/2102.06183
Code: https://github.com/jayleicn/ClipBERT
41. Self-attention based Text Knowledge Mining for Text Detection
Paper: None
Code: https://github.com/CVI-SZU/STKM
42. SSAN: Separable Self-Attention Network for Video Representation Learning
Paper: None
Code: None
43. Scaling Local Self-Attention For Parameter Efficient Visual Backbones
Paper(Oral): https://arxiv.org/abs/2103.12731
Code: None
上述43篇Transformer论文下载
后台回复：CVPR2021，即可下载上述论文PDF
CVPR和Transformer资料下载
后台回复：CVPR2021，即可下载CVPR 2021论文和代码开源的论文合集
后台回复：Transformer综述，即可下载最新的两篇Transformer综述PDF
CVer-Transformer交流群成立
扫码添加CVer助手，可申请加入CVer-Transformer 微信交流群，方向已涵盖：目标检测、图像分割、目标跟踪、人脸检测&识别、OCR、姿态估计、超分辨率、SLAM、医疗影像、Re-ID、GAN、NAS、深度估计、自动驾驶、强化学习、车道线检测、模型剪枝&压缩、去噪、去雾、去雨、风格迁移、遥感图像、行为识别、视频理解、图像融合、图像检索、论文投稿&交流、PyTorch和TensorFlow等群。
一定要备注：研究方向+地点+学校/公司+昵称（如Transformer+上海+上交+卡卡），根据格式备注，可更快被通过且邀请进群
▲长按加小助手微信，进交流群▲点击上方卡片，关注CVer公众号
整理不易，请给CVer点赞和在看