mlsanityData to 7 Oct 2026

Meta Generative Attack on Person Reidentification

arXiv 2301.06286 ↗First posted 16 Jan 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks have been recently investigated in person re-identification. These attacks perform well under cross dataset or cross model setting. However, the challenges present in cross-dataset cross-model scenario does not allow these models to achieve similar accuracy. To this end, we propose our method with the goal of achieving better transferability against different models and across datasets. We generate a mask to obtain better performance across models and use meta learning to boost the generalizability in the challenging cross-dataset cross-model setting. Experiments on Market-1501, DukeMTMC-reID and MSMT-17 demonstrate favorable results compared to other attacks.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 16 Jan 2023.

Builds on

34 of 49 references.

References · 34

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  11. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  12. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
22 more
  1. 2020Understanding the Behaviour of Contrastive Losscited by 397
  2. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  3. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  4. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  5. 2020Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-IDcited by 212
  6. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  7. 2020Learning explanations that are hard to varycited by 132
  8. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  9. 2021Feature Importance-aware Transferable Adversarial Attackscited by 125
  10. 2018Dissecting Person Re-identification from the Viewpoint of Viewpointcited by 83
  11. 2017AlignedReID: Surpassing Human-Level Performance in Person Re-Identificationcited by 61
  12. 2018Multi-Level Factorisation Net for Person Re-Identificationcited by 58
  13. 2021Meta Gradient Adversarial Attackcited by 55
  14. 2021SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalizationcited by 50
  15. 2019Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptationcited by 44
  16. 2020Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Rankingcited by 42
  17. 2019advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patternscited by 35
  18. 2018Universal Perturbation Attack Against Image Retrievalcited by 31
  19. 2021QAIR: Practical Query-efficient Black-Box Attacks for Image Retrievalcited by 22
  20. 20203D Face Anti-spoofing with Factorized Bilinear Codingcited by 20
  21. 2021Lightweight Multi-Branch Network for Person Re-Identificationcited by 18
  22. 2021A Simple and Strong Baseline for Universal Targeted Attacks on Siamese Visual Trackingcited by 9

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 2.

5 papers.

  1. 2023MVPatch: More Vivid Patch for Adversarial Camouflaged Attacks on Object Detectors in the Physical Worldcited by 4
  2. 2024Learning to Learn Transferable Generative Attack for Person Re-Identificationcited by 1
  3. 2024Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identificationcited by 0
  4. 2025Modality Unified Attack for Omni-Modality Person Re-Identificationcited by 0
  5. 2025Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversioncited by 0