AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Learning Contrastive Representation for Semantic Correspondence

Taihong Xiao, Sifei Liu, Shalini De Mello, Zhiding Yu, Jan Kautz, Ming–Hsuan Yang

IJCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 15 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 cross-instance pixel-level contrastive learning on PF-PASCAL pairs (ablation)IC baseline · PF-PASCALPCK@0.05: 44.3 -> 51.0Improved
finetune image-level model on PF-PASCAL pairs without pixel loss (ablation)IC baseline · PF-PASCALPCK@0.05: 44.3 -> 43.7No clear effect
add pixel-level contrastive loss on self-augmented ImageNet pairs (ablation)IC baseline · PF-PASCALPCK@0.05: 44.3 -> 38.1Hurt
update backbone with image-level loss instead of freezing it (ablation)IC + PC · PF-PASCALPCK@0.05: 39.5 -> 51.0Improved
add self-attention module for augmentation (ablation)Ours · PF-PASCALPCK@0.05: 49.9 -> 51.0Improved
add regularized Hough matching at test time (ablation)Ours · PF-PASCALPCK@0.05: 45.0 -> 51.0Improved
add OT at test time (ablation)Ours · PF-PASCALPCK@0.05: 41.0 -> 45.0Improved
use pixel contrastive loss for beam search instead of ground truth (ablation)Ours · PF-PASCALPCK@0.05: 53.4 -> 51.0No clear effect
add information entropy regularization (ablation)Ours · PF-WILLOWPCK@0.05: 40.10 -> 43.10Improved
add information entropy regularization (ablation)Ours · PF-PASCALPCK@0.05: 51.00 -> 50.70Hurt
add differentiable OT and RHM layers in training (ablation)Ours · PF-PASCALPCK@0.05: 51.0 -> 32.4Hurt
add concentration loss in training (ablation)Ours · PF-PASCALPCK@0.05: 51.0 -> 48.1No 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