AI Paper Atlas

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

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Natalie Dullerud, Karsten Roth, Kimia Hamidieh, Nicolas Papernot, Marzyeh Ghassemi

ICLR 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 5 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
Train the upstream DML embedding with manually imbalanced rather than balanced classesMargin loss + distance-weighted sampling · CUB200-2011 (bird color)upstream Recall@1 gap: 0.017\pm 0.007 -> 0.212\pm 0.029Hurt
Train the upstream DML embedding with manually imbalanced rather than balanced classesMargin loss + distance-weighted sampling, followed by a balanced downstream classifier · CUB200-2011 (bird color)downstream accuracy gap: 0.014\pm 0.002 -> 0.131\pm 0.027Hurt
Add sensitive-attribute embedding and partial de-correlationMargin loss + distance-weighted sampling · CelebA (skintone)downstream accuracy gap: 0.082 ± 0.005 -> 0.131 ± 0.006Hurt
Add sensitive-attribute embedding and partial de-correlationMargin loss + distance-weighted sampling · LFW (race)downstream accuracy gap: 0.012 ± 0.009 -> 0.009± 0.003Improved
Add sensitive-attribute embedding and partial de-correlationMargin loss + distance-weighted sampling · CUB200-2011 (bird color; manually imbalanced)downstream precision gap: 0.333 ± 0.049 -> 0.317 ± 0.046Improved
Add sensitive-attribute embedding and partial de-correlationTriplet loss + distance-weighted sampling · CUB200-2011 (bird color; manually imbalanced)downstream accuracy gap: 0.154 ± 0.029 -> 0.148 ± 0.049Improved

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