AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-Identification

Yi Zheng, Shixiang Tang, Guolong Teng, Yixiao Ge, Kaijian Liu, Jing Qin, Donglian Qi, Dapeng Chen

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 124 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 cluster split to merge-only hierarchical clustering (ablation)Ours · Duke to Market / Market to DukemAP (%): 75.0 -> 80.0 (D->M); 61.7 -> 70.1 (M->D)Improved
add label propagation to average-linkage hierarchical clustering (ablation)Ours · Duke to Market / Market to DukemAP (%): 53.3 -> 80.0 (D->M); 59.0 -> 70.1 (M->D)Improved
add hierarchical levels to single-level label propagation (ablation)Ours · Duke to Market / Market to DukemAP (%): 74.6 -> 80.0 (D->M); 68.9 -> 70.1 (M->D)Improved
treat each target instance as its own class instead of clustering (ablation)Src. only baseline · Duke to MarketmAP (%): 19.6 -> 6.0Hurt
increase label update interval from online (0) to 3 (ablation)Ours · Duke to Market / Market to DukemAP (%): 80.0 -> 64.2 (D->M); 70.1 -> 62.2 (M->D)Hurt
select anchors by density peak instead of random choosing (ablation)Ours · Duke to MarketmAP (%): 75.0 -> 80.0Improved
select anchors by density peak instead of farthest point sampling (ablation)Ours · Duke to MarketmAP (%): 75.4 -> 80.0Improved
raise merge alpha from 0.1 to 0.99 (ablation)Ours · Duke to MarketmAP (%): 66.9 -> 80.0Improved
raise split alpha from 0.3 to 0.99 (ablation)Ours · Duke to MarketmAP (%): 76.1 -> 80.0Improved
increase number of hierarchy levels from 1 to 2 (ablation)Ours · Duke to Market / Market to DukemAP (%)Improved
increase number of hierarchy levels beyond 2 (ablation)Ours · Duke to Market / Market to DukemAP (%)No clear effect
use online hierarchical cluster dynamics instead of epoch-wise DBSCAN (SpCL), unsupervisedOurs · Market-1501 unsupervisedmAP (%): 73.1 -> 78.1Improved

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