mlsanityData to 7 Oct 2026

Style Variable and Irrelevant Learning for Generalizable Person Re-identification

arXiv 2209.05235 ↗First posted 12 Sep 2022cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Recently, due to the poor performance of supervised person re-identification (ReID) to an unseen domain, Domain Generalization (DG) person ReID has attracted a lot of attention which aims to learn a domain-insensitive model and can resist the influence of domain bias. In this paper, we first verify through an experiment that style factors are a vital part of domain bias. Base on this conclusion, we propose a Style Variable and Irrelevant Learning (SVIL) method to eliminate the effect of style factors on the model. Specifically, we design a Style Jitter Module (SJM) in SVIL. The SJM module can enrich the style diversity of the specific source domain and reduce the style differences of various source domains. This leads to the model focusing on identity-relevant information and being insensitive to the style changes. Besides, we organically combine the SJM module with a meta-learning algorithm, maximizing the benefits and further improving the generalization ability of the model. Note that our SJM module is plug-and-play and inference cost-free. Extensive experiments confirm the effectiveness of our SVIL and our method outperforms the state-of-the-art methods on DG-ReID benchmarks by a large margin.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 49 of its 73 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

49 of 73 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  4. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  5. 2017In Defense of the Triplet Loss for Person Re-Identificationcited by 784
  6. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  7. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  8. 2013Domain Generalization via Invariant Feature Representationcited by 622
  9. 2021Domain Generalization with MixStylecited by 563
  10. 2020Deep Learning for Person Re-identification: A Survey and Outlookcited by 547
  11. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  12. 2021TransReID: Transformer-based Object Re-Identificationcited by 432
37 more
  1. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  2. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
  3. 2016A Learned Representation For Artistic Stylecited by 340
  4. 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
  5. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  6. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  7. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  8. 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
  9. 2017Improved Texture Networks: Maximizing Quality and Diversity in Feed-forward Stylization and Texture Synthesiscited by 215
  10. 2020Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identificationcited by 214
  11. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  12. 2021AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfercited by 178
  13. 2017Demystifying Neural Style Transfercited by 152
  14. 2020Style Normalization and Restitution for Generalizable Person Re-identificationcited by 136
  15. 2020Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identificationcited by 110
  16. 2016Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesiscited by 102
  17. 2020Meta Batch-Instance Normalization for Generalizable Person Re-Identificationcited by 77
  18. 2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
  19. 2017Unsupervised Person Re-identification: Clustering and Fine-tuningcited by 73
  20. 2019Learning Generalisable Omni-Scale Representations for Person Re-Identificationcited by 73
  21. 2018Unsupervised Domain Adaptive Re-Identification: Theory and Practicecited by 69
  22. 2021Cloth-Changing Person Re-identification from A Single Image with Gait Prediction and Regularizationcited by 69
  23. 2021Lifelong Person Re-Identification via Adaptive Knowledge Accumulationcited by 57
  24. 2019Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practicecited by 48
  25. 2019Vehicle Re-identification with Viewpoint-aware Metric Learningcited by 45
  26. 2017Multi-scale Deep Learning Architectures for Person Re-identificationcited by 44
  27. 2019A survey of advances in vision-based vehicle re-identificationcited by 36
  28. 2021CrossNorm and SelfNorm for Generalization under Distribution Shiftscited by 33
  29. 2018RAM: A Region-Aware Deep Model for Vehicle Re-Identificationcited by 30
  30. 2020Multi-Domain Adversarial Feature Generalization for Person Re-Identificationcited by 22
  31. 2019Adaptive Exploration for Unsupervised Person Re-Identificationcited by 17
  32. 2019Augmented Hard Example Mining for Generalizable Person Re-Identificationcited by 11
  33. 2021Agent-Centric Relation Graph for Object Visual Navigationcited by 10
  34. 2021Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identificationcited by 9
  35. 2016PersonNet: Person Re-identification with Deep Convolutional Neural Networkscited by 8
  36. 2020Unsupervised Domain Adaptation in Person re-ID via k-Reciprocal Clustering and Large-Scale Heterogeneous Environment Synthesiscited by 5
  37. 2019Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Liftingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Multi-Grained Vision-Language Alignment for Domain Generalized Person Re-Identificationcited by 0
  2. 2026Multimodal LLM-Empowered Re-Ranking for Generalizable Person Re-Identificationcited by 0