mlsanityData to 14 Oct 2026

Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval

arXiv 2312.07364 ↗First posted 12 Dec 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Adversarial training has achieved substantial performance in defending image retrieval against adversarial examples. However, existing studies in deep metric learning (DML) still suffer from two major limitations: weak adversary and model collapse. In this paper, we address these two limitations by proposing Collapse-Aware TRIplet DEcoupling (CA-TRIDE). Specifically, TRIDE yields a stronger adversary by spatially decoupling the perturbation targets into the anchor and the other candidates. Furthermore, CA prevents the consequential model collapse, based on a novel metric, collapseness, which is incorporated into the optimization of perturbation. We also identify two drawbacks of the existing robustness metric in image retrieval and propose a new metric for a more reasonable robustness evaluation. Extensive experiments on three datasets demonstrate that CA-TRIDE outperforms existing defense methods in both conventional and new metrics. Codes are available at https://github.com/michaeltian108/CA-TRIDE.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 12 Dec 2023.

Builds on

27 of 36 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  5. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  6. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  7. 2019Multi-Similarity Loss with General Pair Weighting for Deep Metric Learningcited by 368
  8. 2020A Metric Learning Reality Checkcited by 321
  9. 2017Sampling Matters in Deep Embedding Learningcited by 285
  10. 2014Learning Fine-grained Image Similarity with Deep Rankingcited by 190
  11. 2017Deep Metric Learning with Angular Losscited by 107
  12. 2020Revisiting Training Strategies and Generalization Performance in Deep Metric Learningcited by 100
15 more
  1. 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
  2. 2020Hard negative examples are hard, but usefulcited by 82
  3. 2020Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Rankingcited by 42
  4. 2020Targeted Attack for Deep Hashing based Retrievalcited by 35
  5. 2018Universal Perturbation Attack Against Image Retrievalcited by 32
  6. 2019Adversarial Learning with Margin-based Triplet Embedding Regularizationcited by 29
  7. 2019Targeted Mismatch Adversarial Attack: Query with a Flower to Retrieve the Towercited by 26
  8. 2021QAIR: Practical Query-efficient Black-Box Attacks for Image Retrievalcited by 22
  9. 2021Understanding the Interaction of Adversarial Training with Noisy Labelscited by 19
  10. 2021Adversarial Robustness via Fisher-Rao Regularizationcited by 19
  11. 2020Adversarial Attack on Deep Product Quantization Network for Image Retrievalcited by 13
  12. 2019Who's Afraid of Adversarial Queries? The Impact of Image Modifications on Content-based Image Retrievalcited by 10
  13. 2022Enhancing Adversarial Robustness for Deep Metric Learningcited by 10
  14. 2021Practical Relative Order Attack in Deep Rankingcited by 9
  15. 2021Adversarial Attack and Defense in Deep Rankingcited by 8

Built on by

Cited by year

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

2 papers.

  1. 2024GSSF: Generalized Structural Sparse Function for Deep Cross-modal Metric Learningcited by 4
  2. 2025Pay Less Attention to Function Words for Free Robustness of Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Unsupervised Multi-Criteria Adversarial Detection in Deep Image Retrieval
  2. 2026Why Training-Free Token Reduction Collapses: The Inherent Instability of Pairwise Scoring Signals
  3. 2025RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking
  4. 2026Decoupling Defense Strategies for Robust Image Watermarking
  5. 2025Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval
  6. 2025Adversarial Reconstruction Feedback for Robust Fine-grained Generalization
  7. 2024Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
  8. 2024Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Models