AI Paper Atlas

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

A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses

Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko, Eric Granger, Marco Pedersoli, Pablo Piantanida, Ismail Ben Ayed

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive representation theory · 152 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
evaluate with cosine distance instead of Euclidean distance on unnormalized featuresCross-Entropy (ResNet-50) · CUB-200-2011Recall@1: 67.6 -> 69.2Improved
evaluate with cosine distance instead of Euclidean distance on unnormalized featuresCross-Entropy (ResNet-50) · Cars-196Recall@1: 89.1 -> 89.3No clear effect
evaluate with cosine distance instead of Euclidean distance on unnormalized featuresCross-Entropy (ResNet-50) · Stanford Online ProductsRecall@1: 80.8 -> 81.1No clear effect
evaluate with cosine distance instead of Euclidean distance on unnormalized featuresCross-Entropy (ResNet-50) · In-Shop Clothes RetrievalRecall@1: 90.6 -> 90.6No clear effect
add l2-normalization of features during training (ablation)Cross-Entropy (ResNet-50) · four DML benchmarksRecallHurt
add batch normalization (no scale or bias) on top of the feature extractor (ablation)Cross-Entropy (ResNet-50) · Cars, SOP, In-ShopRecallImproved
add batch normalization (no scale or bias) on top of the feature extractor (ablation)Cross-Entropy (ResNet-50) · CUB-200-2011RecallHurt
add random jittering of brightness, contrast and saturation (ablation)Cross-Entropy (ResNet-50) · CUB and CarsRecallImproved
tune the learning rate per dataset rather than sharing one (ablation)Cross-Entropy (ResNet-50) · four DML benchmarksRecallImproved
train with simplified pairwise cross-entropy (SPCE) instead of cross-entropysmall CNN · MNISTvalidation accuracyNo 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