Research map / Label-efficient and robust learning / Recognition and long-tail
View Confusion Feature Learning for Person Re-Identification
Fangyi Liu, Lei Zhang
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 SIFT guided loss (ablation) | VCFL (GoogLeNet) · CUHK03 (Detected) | mAP: 81.51 -> 83.70 | Improved |
| add SIFT guided loss (ablation) | VCFL (GoogLeNet) · Market1501 | mAP: 56.43 -> 58.60 | Improved |
| add SIFT guided loss (ablation) | VCFL (GoogLeNet) · CUHK01-100 | top-1: 88.1 -> 86.2 | Hurt |
| add view classifier based (adversarial) confusion alone (ablation) | triplet baseline (ResNet50) · Market1501 | mAP: 70.91 -> 69.04 | Hurt |
| add feature based confusion alone (ablation) | triplet baseline (ResNet50) · Market1501 | mAP: 70.91 -> 73.21 | Improved |
| add SIFT based confusion alone (ablation) | triplet baseline (ResNet50) · Market1501 | mAP: 70.91 -> 74.30 | Improved |
| combine all three confusion terms (ablation) | triplet baseline (ResNet50) · Market1501 | top-1: 86.58 -> 89.25 | Improved |
| combine all three confusion terms versus SIFT term alone (ablation) | VCFL (ResNet50) · Market1501 | mAP: 74.30 -> 74.48 | No clear effect |
| add view confusion | GoogLeNet baseline · Market1501 | mAP: 55.6 -> 58.60 | Improved |
| add view confusion | GoogLeNet baseline · CUHK03 (Detected) | top-1: 71.7 -> 76.07 | Improved |
| add view confusion | triplet baseline (ResNet50) · CUHK03 (Detected) | mAP: 53.71 -> 55.61 | Improved |
| add re-ranking to VCFL | VCFL (ResNet50) · Market1501 | mAP: 74.48 -> 86.67 | Improved |
Closest papers by meaning
- Person Re-Identification by Camera Correlation Aware Feature Augmentation (TPAMI 2017 · similarity 0.89)
- Deep Learning for Person Re-Identification: A Survey and Outlook (TPAMI 2021 · similarity 0.87)
- Revisiting Person Re-Identification by Camera Selection (TPAMI 2023 · similarity 0.86)
- Intra-Inter Camera Similarity for Unsupervised Person Re-Identification (CVPR 2021 · similarity 0.86)
- Ordered or Orderless: A Revisit for Video Based Person Re-Identification (TPAMI 2020 · similarity 0.86)
- Unsupervised Person Re-Identification by Deep Asymmetric Metric Embedding (TPAMI 2018 · 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.
