AI Paper Atlas

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

MIC: Mining Interclass Characteristics for Improved Metric Learning

Karsten Roth, Biagio Brattoli, Bjorn Ommer

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 96 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 clustering-based auxiliary encoder without standardization (ablation)margin loss baseline · CUB200-2011Recall@1: 62.9 -> 59.1Hurt
add clustering-based auxiliary encoder without standardization (ablation)margin loss baseline · CARS196Recall@1: 80.0 -> 79.2Hurt
add class-wise standardization before clustering (ablation)MIC · CUB200-2011Recall@1: 59.1 -> 64.9Improved
add class-wise standardization before clustering (ablation)MIC · CARS196Recall@1: 79.2 -> 81.3Improved
add class-wise standardization before clustering (ablation)MIC · Stanford Online ProductsRecall@1: 71.9 -> 75.8Improved
add mutual information loss between encoders (ablation)MIC · CUB200-2011Recall@1: 64.9 -> 66.1Improved
add mutual information loss between encoders (ablation)MIC · CARS196Recall@1: 81.3 -> 82.6Improved
add mutual information loss between encoders (ablation)MIC · Stanford Online ProductsRecall@1: 75.8 -> 77.2Improved
apply MIC on margin lossMargin* · CUB200-2011Recall@1: 62.9 -> 66.1Improved
apply MIC on margin lossMargin* · In-Shop ClothesRecall@1: 84.5 -> 88.2Improved
apply MIC on ProxyNCAProxyNCA* · CARS196Recall@1: 73.0 -> 75.9Improved
apply MIC on semihard triplet lossSemihard* · CARS196Recall@1: 65.5 -> 70.5Improved

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