Research map / Label-efficient and robust learning / Recognition and long-tail
Person Re-Identification by Camera Correlation Aware Feature Augmentation
Ying-Cong Chen, Xiatian Zhu, Wei‐Shi Zheng, Jianhuang Lai
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 CVD regularization to CRAFT (ablation) | CRAFT (kernelized, MFA) · VIPeR | rank-1 (%): 46.3 -> 50.3 | Improved |
| add CVD regularization to CRAFT (ablation) | CRAFT (kernelized, MFA) · CUHK01 | rank-1 (%): 73.8 -> 74.5 | Improved |
| add CVD regularization to CRAFT (ablation) | CRAFT (kernelized, MFA) · CUHK03 | rank-1 (%): 83.9 -> 84.3 | Improved |
| add CVD regularization to CRAFT (ablation) | CRAFT (kernelized, MFA) · Market-1501 | rank-1 (%): 66.6 -> 68.7 | Improved |
| add CVD regularization to CRAFT (ablation) | CRAFT (kernelized, MFA) · QMUL GRID | rank-1 (%): 15.8 -> 22.4 | Improved |
| replace original features with camera-correlation-aware augmentation (CRAFT) | MFA, no kernel · VIPeR | rank-1 (%): 43.3 -> 47.8 | Improved |
| replace zero-padding augmentation with CRAFT | MFA, no kernel · Market-1501 | rank-1 (%): 38.2 -> 67.9 | Improved |
| use zero-padding augmentation instead of original features | MFA, no kernel · VIPeR | rank-1 (%): 43.3 -> 37.5 | Hurt |
| use baseline feature augmentation instead of original features | MFA, no kernel · CUHK01 | rank-1 (%): 64.3 -> 59.0 | Hurt |
| add Bhattacharyya kernelization to CRAFT | CRAFT (MFA) · VIPeR | rank-1 (%): 47.8 -> 50.3 | Improved |
| add Bhattacharyya kernelization to CRAFT | CRAFT (MFA) · QMUL GRID | rank-1 (%): 25.4 -> 22.4 | Hurt |
| replace TFLDA domain adaptation with CRAFT | re-id model · CUHK03 | rank-1 (%): 76.7 -> 84.3 | Improved |
Closest papers by meaning
- Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding (TPAMI 2018 · similarity 0.92)
- Deep Learning for Person Re-Identification: A Survey and Outlook (TPAMI 2021 · similarity 0.91)
- A Systematic Evaluation and Benchmark for Person Re-Identification: Features, Metrics, and Datasets (TPAMI 2018 · similarity 0.91)
- Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification (ECCV 2020 · similarity 0.91)
- Joint Discriminative and Generative Learning for Person Re-Identification (CVPR 2019 · similarity 0.91)
- Exploring the Camera Bias of Person Re-identification (ICLR 2025 · similarity 0.89)
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.
