mlsanityData to 13 Oct 2026

TransReID: Transformer-based Object Re-Identification

arXiv 2102.04378 ↗First posted 8 Feb 2021cs.CVcited by 432

Not on the map. Why?

Abstract (arXiv)

Extracting robust feature representation is one of the key challenges in object re-identification (ReID). Although convolution neural network (CNN)-based methods have achieved great success, they only process one local neighborhood at a time and suffer from information loss on details caused by convolution and downsampling operators (e.g. pooling and strided convolution). To overcome these limitations, we propose a pure transformer-based object ReID framework named TransReID. Specifically, we first encode an image as a sequence of patches and build a transformer-based strong baseline with a few critical improvements, which achieves competitive results on several ReID benchmarks with CNN-based methods. To further enhance the robust feature learning in the context of transformers, two novel modules are carefully designed. (i) The jigsaw patch module (JPM) is proposed to rearrange the patch embeddings via shift and patch shuffle operations which generates robust features with improved discrimination ability and more diversified coverage. (ii) The side information embeddings (SIE) is introduced to mitigate feature bias towards camera/view variations by plugging in learnable embeddings to incorporate these non-visual clues. To the best of our knowledge, this is the first work to adopt a pure transformer for ReID research. Experimental results of TransReID are superior promising, which achieve state-of-the-art performance on both person and vehicle ReID benchmarks.

Key facts. Cited by 432 papers in the map (data through 13 Oct 2026). Builds on 61 of its 80 references that are in the map. First posted on arXiv 8 Feb 2021.

Builds on

61 of 80 references.

References · 61

  1. 2017Attention Is All You Needcited by 60,106
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,950
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  4. 2020End-to-End Object Detection with Transformerscited by 7,396
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,713
  6. 2020Training data-efficient image transformers & distillation through attentioncited by 4,574
  7. 2017Non-local Neural Networkscited by 2,291
  8. 2017Decoupled Weight Decay Regularizationcited by 1,788
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  10. 2017Random Erasing Data Augmentationcited by 1,238
  11. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,199
  12. 2021Transformers in Vision: A Surveycited by 1,010
38 more
  1. 2016Deep Networks with Stochastic Depthcited by 977
  2. 2020Pre-Trained Image Processing Transformercited by 892
  3. 2018Image Transformercited by 771
  4. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 687
  5. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 551
  6. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  7. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  8. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
  9. 2020ResNeSt: Split-Attention Networkscited by 445
  10. 2019Reducing Transformer Depth on Demand with Structured Dropoutcited by 436
  11. 2019Bag of Tricks and A Strong Baseline for Deep Person Re-identificationcited by 429
  12. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  13. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  14. 2018Video Action Transformer Networkcited by 316
  15. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  16. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 290
  17. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  18. 2020Training with Quantization Noise for Extreme Model Compressioncited by 145
  19. 2020Lite Transformer with Long-Short Range Attentioncited by 127
  20. 2019ABD-Net: Attentive but Diverse Person Re-Identificationcited by 126
  21. 2019Relation-Aware Global Attention for Person Re-identificationcited by 124
  22. 2020Identity-Guided Human Semantic Parsing for Person Re-Identificationcited by 118
  23. 2018How to Start Training: The Effect of Initialization and Architecturecited by 109
  24. 2020High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identificationcited by 105
  25. 2020ConvBERT: Improving BERT with Span-based Dynamic Convolutioncited by 88
  26. 2020Toward Transformer-Based Object Detectioncited by 84
  27. 2018Dissecting Person Re-identification from the Viewpoint of Viewpointcited by 83
  28. 2016A Discriminatively Learned CNN Embedding for Person Re-identificationcited by 78
  29. 2019Mixed High-Order Attention Network for Person Re-Identificationcited by 65
  30. 2018Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approachcited by 58
  31. 2018Densely Semantically Aligned Person Re-Identificationcited by 58
  32. 2019Foreground-aware Pyramid Reconstruction for Alignment-free Occluded Person Re-identificationcited by 55
  33. 2020Parsing-based View-aware Embedding Network for Vehicle Re-Identificationcited by 53
  34. 2017Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identificationcited by 52
  35. 2019Semantics-Aligned Representation Learning for Person Re-identificationcited by 51
  36. 2019Vehicle Re-identification with Viewpoint-aware Metric Learningcited by 45
  37. 2017Deep Representation Learning with Part Loss for Person Re-Identificationcited by 44
  38. 2016End-to-End Comparative Attention Networks for Person Re-identificationcited by 42

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 49; 2022: 60; 2023: 87; 2024: 84; 2025: 87; 2026: 65.

432 papers.

Sort:

By area:

  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,930
  2. 2021Multiscale Vision Transformerscited by 896
  3. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
  4. 2022Multimodal Learning with Transformers: A Surveycited by 399
  5. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  6. 2022UniFormer: Unifying Convolution and Self-attention for Visual Recognitioncited by 206
  7. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labelscited by 178
  8. 2021MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimationcited by 151
  9. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143
  10. 2021TransFG: A Transformer Architecture for Fine-grained Recognitioncited by 131
  11. 2023Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrievalcited by 131
  12. 2021CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptationcited by 129
38 more
  1. 2021PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformercited by 118
  2. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  3. 2021Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimationcited by 94
  4. 2023Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Taskscited by 94
  5. 2023Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformerscited by 79
  6. 2022Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identificationcited by 78
  7. 2021Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformercited by 68
  8. 2021KVT: k-NN Attention for Boosting Vision Transformerscited by 65
  9. 2021BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Searchcited by 63
  10. 2023UniHCP: A Unified Model for Human-Centric Perceptionscited by 59
  11. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  12. 2022Accelerating DETR Convergence via Semantic-Aligned Matchingcited by 58
  13. 2021Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNscited by 57
  14. 2022A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localizationcited by 56
  15. 2021On Pursuit of Designing Multi-modal Transformer for Video Groundingcited by 54
  16. 2021GiT: Graph Interactive Transformer for Vehicle Re-identificationcited by 49
  17. 2023PLIP: Language-Image Pre-training for Person Representation Learningcited by 49
  18. 2021AAformer: Auto-Aligned Transformer for Person Re-Identificationcited by 48
  19. 2023PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformercited by 47
  20. 2023Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructionscited by 46
  21. 2021Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identificationcited by 44
  22. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  23. 2021TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detectioncited by 41
  24. 2021Feature Erasing and Diffusion Network for Occluded Person Re-Identificationcited by 41
  25. 2022Learning Progressive Modality-shared Transformers for Effective Visible-Infrared Person Re-identificationcited by 40
  26. 2021HAT: Hierarchical Aggregation Transformers for Person Re-identificationcited by 39
  27. 2022Residual Mixture of Expertscited by 39
  28. 2023HumanBench: Towards General Human-centric Perception with Projector Assisted Pretrainingcited by 38
  29. 2021Self-Supervised Pre-Training for Transformer-Based Person Re-Identificationcited by 36
  30. 2023Part-Aware Transformer for Generalizable Person Re-identificationcited by 35
  31. 2024Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identificationcited by 35
  32. 2023DilateFormer: Multi-Scale Dilated Transformer for Visual Recognitioncited by 34
  33. 2025Chat-Driven Text Generation and Interaction for Person Retrievalcited by 34
  34. 2022Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformerscited by 33
  35. 2023HAP: Structure-Aware Masked Image Modeling for Human-Centric Perceptioncited by 33
  36. 2023SG-Former: Self-guided Transformer with Evolving Token Reallocationcited by 32
  37. 2023TOP-ReID: Multi-spectral Object Re-Identification with Token Permutationcited by 32
  38. 2022Cascade Transformers for End-to-End Person Searchcited by 31

50 most cited of 432 All 432 (JSON)