AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification

Jiangming Shi, Yachao Zhang, Xiangbo Yin, Yuan Xie, Zhizhong Zhang, Jianping Fan, Zhongchao Shi, Yanyun Qu

ICCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 76 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
use DPIS dual pseudo-label self-training instead of OTLAvisible-infrared ReID · SYSU-MM01 all-search, uni-semi-supervisedRank-1: 48.2 -> 58.4Improved
apply existing unsupervised domain adaptation methodsvisible-infrared ReID · SYSU-MM01 all-search, uni-semi-supervisedRank-1: 7.3 to 15.1 Rank-1 for UDA methodsNo clear effect
add hybrid pseudo-labels (DPI) to the visible-label baseline (ablation)baseline · SYSU-MM01 all-searchRank-1: 3.80 -> 36.56Improved
add NLP on top of DPI (ablation)DPIS · SYSU-MM01 all-searchRank-1: 36.56 -> 51.90Improved
add NCC and UAL on top of DPI and NLP (ablation)DPIS · SYSU-MM01 all-searchRank-1: 51.90 -> 58.40Improved
use DPIS in the bi-semi-supervised setting versus re-implemented supervised methodsvisible-infrared ReID · SYSU-MM01 all-search, 10% labelsRank-1: 37.90 -> 57.70 (vs DART)Improved
compare DPIS (uni-semi-supervised) against fully supervised methodsvisible-infrared ReID · SYSU-MM01 all-searchRank-1: 58.4 vs LUPI 71.1Mixed
vary hyper-parameter tau_sam in the unreliable anchor loss from 6 to 14 (ablation)DPIS · SYSU-MM01 all-searchRank-1No clear effect

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