Research map / Label-efficient and robust learning / Recognition and long-tail
Attack-Guided Perceptual Data Generation for Real-World Re-Identification
Yukun Huang, Xueyang Fu, Zheng-Jun Zha
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add generated samples trained with plain cross-entropy only (ablation) | ResNet-50 baseline · MLR-CUHK03 | Rank-1 (%): 78.1 -> 75.2 | Hurt |
| add self-center loss and Wasserstein loss on generated samples (ablation) | GAAG naive · MLR-CUHK03 | Rank-1 (%): 75.2 -> 87.6 | Improved |
| add synthetic-to-real feature constraints (ablation) | GAAG naive · MLR-VIPeR | Rank-1 (%): 29.7 -> 52.2 | Improved |
| add global-aware dense augmentation (ablation) | GAAG · MLR-CUHK03 | Rank-1 (%): 84.8 -> 87.6 | Improved |
| add global-aware dense augmentation (ablation) | GAAG · MLR-VIPeR | Rank-1 (%): 49.7 -> 52.2 | Improved |
| add global-aware dense augmentation (ablation) | GAAG · CAVIAR | Rank-1 (%): 43.8 -> 44.0 | No clear effect |
| add ReID-driven perceptual attack guidance (ablation) | GAAG · MLR-CUHK03 | Rank-1 (%): 86.1 -> 87.6 | Improved |
| add ReID-driven perceptual attack guidance (ablation) | GAAG · MLR-VIPeR | Rank-1 (%): 51.3 -> 52.2 | Improved |
| add ReID-driven perceptual attack guidance (ablation) | GAAG · CAVIAR | Rank-1 (%): 41.6 -> 44.0 | Improved |
| add random down-sampling augmentation with probability 0.5 (ablation) | ResNet-50 baseline · MLR-CUHK03 | Rank-1 (%): 78.1 -> 76.3 | Hurt |
| add random down-sampling augmentation with probability 0.5 (ablation) | ResNet-50 baseline · CAVIAR | Rank-1 (%): 25.8 -> 21.4 | Hurt |
| add GAAG perceptual data generation (illumination degradation) | ResNet-50 baseline · MSMT17 | Rank-1 (%): 64.0 -> 73.3 | Improved |
Closest papers by meaning
- Towards Robust Person Re-Identification by Defending Against Universal Attackers (TPAMI 2022 · similarity 0.89)
- Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning (AAAI 2021 · similarity 0.89)
- Joint Discriminative and Generative Learning for Person Re-Identification (CVPR 2019 · similarity 0.88)
- A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets (TPAMI 2018 · similarity 0.88)
- Camera-Aware Proxies for Unsupervised Person Re-Identification (AAAI 2021 · similarity 0.87)
- Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic (ICLR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
