AI Paper Atlas

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

Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification

Xudong Tian, Zhizhong Zhang, Shaohui Lin, Yanyun Qu, Yuan Xie, Lizhuang Ma

CVPR 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Supervised person re-identification · 160 citations (OpenAlex)

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 the full VSD, VCD, and VML method instead of the three-branch baseline (ablation)Cross-modal person Re-ID · SYSU-MM01 all-search single-shotRank-1: 48.82 -> 60.02Improved
Add information bottleneck branches without variational distillation (ablation)Three-branch Re-ID baseline · SYSU-MM01 all-search single-shotRank-1: 48.82 -> 54.85Improved
Replace variational distillation with conventional IB (ablation)Three-branch Re-ID model · SYSU-MM01 all-search single-shotRank-1: 60.02 -> 8.79Hurt
Add VSD to the modality-specific branches (ablation)Three-branch Re-ID model · SYSU-MM01 all-search single-shotRank-1: 54.85 -> 59.62Improved
Add VCD and VML to the modality-shared branch (ablation)VSD Re-ID model · SYSU-MM01 all-search single-shotRank-1: 59.62 -> 60.02Improved
Use the full variational distillation method rather than the strongest listed baselineCross-modal person Re-ID · RegDB visible-to-thermalRank-1: 70.9 -> 73.2Improved
Use the full variational distillation method rather than the strongest listed baselineCross-modal person Re-ID · RegDB thermal-to-visibleRank-1: 68.1 -> 71.8Improved
Avoid the mutual-information estimator used by conventional IBRe-ID training · Training timetraining time: 1.26x -> 1.09xImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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