Research map / Label-efficient and robust learning / Recognition and long-tail
An Attention-driven Two-stage Clustering Method for Unsupervised Person Re-Identification
Zilong Ji, Xiaolong Zou, Xiaohan Lin, Xiao Liu, Tiejun Huang, Si Wu
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 voxel attention to two-stage clustering (ablation) | ADTC · DukeMTMC to Market1501 | mAP: 41.1 -> 59.7 | Improved |
| add voxel attention to two-stage clustering (ablation) | ADTC · Market1501 to DukeMTMC | mAP: 28.2 -> 52.5 | Improved |
| add two-stage clustering to voxel attention (ablation) | ADTC · DukeMTMC to Market1501 | mAP: 35.5 -> 59.7 | Improved |
| add two-stage clustering to voxel attention (ablation) | ADTC · Market1501 to DukeMTMC | mAP: 32.6 -> 52.5 | Improved |
| add spatial attention to channel attention (ablation) | ADTC · DukeMTMC to Market1501 | mAP: 42.8 -> 59.7 | Improved |
| add channel attention to spatial attention (ablation) | ADTC · DukeMTMC to Market1501 | mAP: 41.3 -> 59.7 | Improved |
| replace harmonious attention with voxel attention (ablation) | ADTC · DukeMTMC to Market1501 | mAP: 50.6 -> 59.7 | Improved |
| replace CBAM attention with voxel attention (ablation) | ADTC · Market1501 to DukeMTMC | mAP: 49.1 -> 52.5 | Improved |
| add source-domain initialization (ablation) | ADTC · DukeMTMC to Market1501 | mAP: 38.8 -> 59.7 | Improved |
| add voxel attention to progressive clustering (ablation) | ADTC · DukeMTMC | rank-1: 60.3% -> 71.9% | Improved |
| add voxel attention to progressive clustering (ablation) | ADTC · DukeMTMC in-camera errors | number of in-camera errors: 588 -> 340 | Improved |
Closest papers by meaning
- Unsupervised Person Re-Identification via Softened Similarity Learning (CVPR 2020 · similarity 0.90)
- Divide-and-Regroup Clustering for Domain Adaptive Person Re-identification (AAAI 2022 · similarity 0.89)
- A Bottom-Up Clustering Approach to Unsupervised Person Re-Identification (AAAI 2019 · similarity 0.89)
- Tracklet Self-Supervised Learning for Unsupervised Person Re-Identification (AAAI 2020 · similarity 0.89)
- AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification (CVPR 2020 · similarity 0.89)
- Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification (ICCV 2019 · 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.
