AI Paper Atlas

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

Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss

Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Arechiga, Tengyu Ma

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 226 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
Use LDAM-DRW instead of RWImbalanced IMDB review classification · IMDB validationmean error: 23.66 -> 17.84Improved
Add deferred re-weighting to LDAM (ablation)iNaturalist 2018 · iNaturalist 2018 validationTop-1 error: 35.42 -> 32.00Improved
Add deferred re-weighting to ERM (ablation)iNaturalist 2018 · iNaturalist 2018 validationTop-1 error: 42.86 -> 36.27Improved
Use LDAM instead of ERM cross-entropy (ablation)Imbalanced CIFAR-10, long-tailed, ratio 100 · Imbalanced CIFAR-10, long-tailed, ratio 100Top-1 validation error: 29.64 -> 26.65Improved
Add DRW to LDAM (ablation)Imbalanced CIFAR-10, long-tailed, ratio 100 · Imbalanced CIFAR-10, long-tailed, ratio 100Top-1 validation error: 26.65 -> 22.97Improved
Replace class-independent margins with label-distribution-aware margins (ablation)CIFAR-100 with DRW, long-tailed, ratio 100 · Imbalanced CIFAR-100, long-tailed, ratio 100Top-1 validation error: 59.49 -> 57.96Improved
Use DRW with LDAM rather than LDAM with the standard SGD schedule (ablation)Imbalanced Tiny ImageNet, long-tailed, ratio 100 · Imbalanced Tiny ImageNet, long-tailed, ratio 100Top-1 validation error: 64.04 -> 62.53Improved
Use deferred re-sampling instead of deferred re-weighting (ablation)Imbalanced CIFAR-10, long-tailed, ratio 100 · Imbalanced CIFAR-10, long-tailed, ratio 100Top-1 validation error: 25.14 -> 25.50No clear effect
Use deferred re-weighting rather than standard ERM training (ablation)Imbalanced Tiny ImageNet, step, ratio 100 · Imbalanced Tiny ImageNet, step, ratio 100Top-1 validation error: 63.82 -> 62.36Improved
Use LDAM rather than ERM cross-entropy (ablation)Imbalanced Tiny ImageNet, step, ratio 10 · Imbalanced Tiny ImageNet, step, ratio 10Top-1 validation error: 50.89 -> 49.08Improved
Apply Class-Balanced Softmax rather than ERM (ablation)Imbalanced Tiny ImageNet, step, ratio 100 · Imbalanced Tiny ImageNet, step, ratio 100Top-1 validation error: 63.82 -> 74.90Hurt
Replace LDAM with uniform-margin cross-entropy in the DRW method (ablation)Imbalanced CIFAR-10, step, ratio 100 · Imbalanced CIFAR-10, step, ratio 100Top-1 validation error: 23.08 -> 27.67Hurt

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