AI Paper Atlas

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

ICCV 2025 · Label-efficient and robust learning › Semi-supervised learning · approach: Confidence-based pseudo-label selection · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
add neighbor prototype labeling (NPL) on top of DPL (ablation)SPRED (10% labels) · Semi-LReID seen domainsSeen-Avg mAP: 28.8 -> 38.0Improved
add DKCP pseudo-label purification (ablation)SPRED (10% labels) · Semi-LReID seen domainsSeen-Avg mAP: 38.0 -> 43.2Improved
add DPL to base (ablation)LSTKC base · Semi-LReID seen domainsSeen-Avg mAP: 27.7 -> 28.8Improved
add OKAC (old-knowledge clustering) to purification (ablation)DPL+NPL · Semi-LReIDSeen-Avg mAP: 38.0 -> 39.6Improved
add NKC (new-knowledge clustering) to purification (ablation)DPL+NPL · Semi-LReIDSeen-Avg mAP: 38.0 -> 40.1Improved
use both OKAC and NKC together (ablation)DKCP · Semi-LReIDSeen-Avg mAP: 40.1 -> 43.2Improved
use previous DANet to align old model to new data (ablation)SPRED · Semi-LReIDSeen-Avg mAP: 42.5 -> 43.2Improved
add strong-weak SSL augmentation (SPRED double-dagger)SPRED · Semi-LReID 10% labelsSeen-Avg mAP: 43.2 -> 44.8Improved
SPRED vs HDC at 50% label rateSPRED · Semi-LReID 50% labelsSeen-Avg R@1: 60.8 vs 61.2Hurt
add SSL methods plus LSTKC anti-forgetting to LReIDLSTKC · Semi-LReID 10% labelsSeen-Avg mAP: 27.7 -> 32.3 (ShrinkM); 27.7 -> 27.5 (HDC)Mixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy