Research map / Label-efficient and robust learning / Semi-supervised learning
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
Kunlun Xu, Fan Zhuo, Jiangmeng Li, Xu Zou, Jiahuan Zhou
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 neighbor prototype labeling (NPL) on top of DPL (ablation) | SPRED (10% labels) · Semi-LReID seen domains | Seen-Avg mAP: 28.8 -> 38.0 | Improved |
| add DKCP pseudo-label purification (ablation) | SPRED (10% labels) · Semi-LReID seen domains | Seen-Avg mAP: 38.0 -> 43.2 | Improved |
| add DPL to base (ablation) | LSTKC base · Semi-LReID seen domains | Seen-Avg mAP: 27.7 -> 28.8 | Improved |
| add OKAC (old-knowledge clustering) to purification (ablation) | DPL+NPL · Semi-LReID | Seen-Avg mAP: 38.0 -> 39.6 | Improved |
| add NKC (new-knowledge clustering) to purification (ablation) | DPL+NPL · Semi-LReID | Seen-Avg mAP: 38.0 -> 40.1 | Improved |
| use both OKAC and NKC together (ablation) | DKCP · Semi-LReID | Seen-Avg mAP: 40.1 -> 43.2 | Improved |
| use previous DANet to align old model to new data (ablation) | SPRED · Semi-LReID | Seen-Avg mAP: 42.5 -> 43.2 | Improved |
| add strong-weak SSL augmentation (SPRED double-dagger) | SPRED · Semi-LReID 10% labels | Seen-Avg mAP: 43.2 -> 44.8 | Improved |
| SPRED vs HDC at 50% label rate | SPRED · Semi-LReID 50% labels | Seen-Avg R@1: 60.8 vs 61.2 | Hurt |
| add SSL methods plus LSTKC anti-forgetting to LReID | LSTKC · Semi-LReID 10% labels | Seen-Avg mAP: 27.7 -> 32.3 (ShrinkM); 27.7 -> 27.5 (HDC) | Mixed |
Closest papers by meaning
- Distribution-Aware Knowledge Aligning and Prototyping for Non-Exemplar Lifelong Person Re-Identification (TPAMI 2025 · similarity 0.92)
- Long Short-Term Knowledge Decomposition and Consolidation for Lifelong Person Re-Identification (TPAMI 2025 · similarity 0.92)
- LSTKC: Long Short-Term Knowledge Consolidation for Lifelong Person Re-identification (AAAI 2024 · similarity 0.91)
- Mitigate Catastrophic Remembering via Continual Self-Paced Dual-Knowledge Purification for Noisy Lifelong Person Re-Identification (TPAMI 2026 · similarity 0.91)
- Distribution-aware Knowledge Prototyping for Non-exemplar Lifelong Person Re-identification (CVPR 2024 · similarity 0.90)
- DKC: Differentiated Knowledge Consolidation for Cloth-Hybrid Lifelong Person Re-identification (CVPR 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.
