AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Self-reinforcing Unsupervised Matching

Jiang Lu, Lei Li, Changshui Zhang

TPAMI 2021 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning

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 DPW alignment distance instead of naive point-wise distance (ablation)DPW · toy matching exampledistance: 1118 -> 654Improved
add self-reinforcing outer SWIM iterations (ablation)SUM · Chinese character and traffic sign matchingmatch accuracy: 3--20%Improved
add inner SLoMa iterations within each SWIM iteration (ablation)SUM · Song->Lishu matchingmatch accuracyImproved
use larger exploration step size alpha (ablation)SUM SWIM · Song->Lishu matchingfinal match accuracyHurt
use one-by-one exploration (alpha=1) instead of alpha=10 (ablation)SUM SWIM · Song->Lishu matchingstabilityImproved
use DPW distance matching instead of point-wise KNN matching (ablation)SUM · Chinese characterstop-1/top-5 accuracyImproved
add local feature adapter learning instead of plain CNN classifierSUM · Chinese characters and traffic signstop-1/top-5 accuracyImproved

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