mlsanityData to 14 Oct 2026

Domain generalization Person Re-identification on Attention-aware multi-operation strategery

arXiv 2210.10409 ↗First posted 19 Oct 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Domain generalization person re-identification (DG Re-ID) aims to directly deploy a model trained on the source domain to the unseen target domain with good generalization, which is a challenging problem and has practical value in a real-world deployment. In the existing DG Re-ID methods, invariant operations are effective in extracting domain generalization features, and Instance Normalization (IN) or Batch Normalization (BN) is used to alleviate the bias to unseen domains. Due to domain-specific information being used to capture discriminability of the individual source domain, the generalized ability for unseen domains is unsatisfactory. To address this problem, an Attention-aware Multi-operation Strategery (AMS) for DG Re-ID is proposed to extract more generalized features. We investigate invariant operations and construct a multi-operation module based on IN and group whitening (GW) to extract domain-invariant feature representations. Furthermore, we analyze different domain-invariant characteristics, and apply spatial attention to the IN operation and channel attention to the GW operation to enhance the domain-invariant features. The proposed AMS module can be used as a plug-and-play module to incorporate into existing network architectures. Extensive experimental results show that AMS can effectively enhance the model's generalization ability to unseen domains and significantly improves the recognition performance in DG Re-ID on three protocols with ten datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 61 references that are in the map. First posted on arXiv 19 Oct 2022.

Builds on

43 of 61 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  4. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  5. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  6. 2017Mixed Precision Trainingcited by 1,156
  7. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  8. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  9. 2021Domain Generalization with MixStylecited by 566
  10. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 499
  11. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 480
  12. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 473
31 more
  1. 2017Universal Style Transfer via Feature Transformscited by 354
  2. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  3. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
  4. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  5. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 215
  6. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  7. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  8. 2019A Strong Baseline and Batch Normalization Neck for Deep Person Re-identificationcited by 155
  9. 2020Style Normalization and Restitution for Generalizable Person Re-identificationcited by 136
  10. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  11. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  12. 2019Switchable Whitening for Deep Representation Learningcited by 106
  13. 2022Semantic-Aware Domain Generalized Segmentationcited by 79
  14. 2018Batch-Instance Normalization for Adaptively Style-Invariant Neural Networkscited by 78
  15. 2020Meta Batch-Instance Normalization for Generalizable Person Re-Identificationcited by 77
  16. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  17. 2019Learning Generalisable Omni-Scale Representations for Person Re-Identificationcited by 74
  18. 2019Unsupervised Domain Adaptation using Feature-Whitening and Consensus Losscited by 67
  19. 2017AlignedReID: Surpassing Human-Level Performance in Person Re-Identificationcited by 61
  20. 2021Domain Generalization via Gradient Surgerycited by 60
  21. 2020Batch Normalization Embeddings for Deep Domain Generalizationcited by 57
  22. 2018Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformationcited by 49
  23. 2019Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practicecited by 48
  24. 2018Batch DropBlock Network for Person Re-identification and Beyondcited by 45
  25. 2021Domain Generalization via Inference-time Label-Preserving Target Projectionscited by 35
  26. 2020Dual Distribution Alignment Network for Generalizable Person Re-Identificationcited by 20
  27. 2018EANet: Enhancing Alignment for Cross-Domain Person Re-identificationcited by 16
  28. 2020Group Whitening: Balancing Learning Efficiency and Representational Capacitycited by 13
  29. 2022Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identificationcited by 10
  30. 2017Large Margin Learning in Set to Set Similarity Comparison for Person Re-identificationcited by 7
  31. 2021Domain-Class Correlation Decomposition for Generalizable Person Re-Identificationcited by 4

Built on by

Not cited yet.