AI Paper Atlas

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

Enhancing Minority Classes by Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification

Jintong Gao, He Zhao, Zhuo Li, Dan dan Guo

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 4 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 OTmix to ERMERM · CIFAR-LT-100 imb100top-1 error (%): 63.2 -> 53.6Improved
replace random CMO pairing with OT-based pairingERM + CMO · CIFAR-LT-10 imb100top-1 error (%): 25.0 -> 21.7Improved
add OTmix to RIDE (3 experts)RIDE · ImageNet-LTtop-1 error (%): 45.1 -> 42.7Improved
add OTmix to ERMERM · iNaturalist 2018top-1 error (%): 39.0 -> 30.5Improved
add OTmix to CutmixCutmix · CIFAR-100 balancedtop-1 error (%): 31.6 -> 28.0Improved
add OTmix to SaliencyMixSaliencyMix · CIFAR-100 balancedtop-1 error (%): 31.2 -> 21.7Improved
use sample-level cost only (ablation)ERM + OTmix · CIFAR-LT-100 imb100top-1 error (%): 53.6 -> 55.1Hurt
use class-level cost only (ablation)ERM + OTmix · CIFAR-LT-100 imb100top-1 error (%): 53.6 -> 54.5Hurt
euclidean distance instead of cosine similarity (ablation)ERM + OTmix · CIFAR-LT-100 imb100top-1 error (%): 53.6 -> 54.1Hurt
keep same-category pairs (do not zero confusion-matrix diagonal) (ablation)ERM + OTmix · CIFAR-LT-100 imb100top-1 error (%): 53.6 -> 54.9Hurt
sample background by probability instead of max transport value (ablation)ERM + OTmix · CIFAR-LT-100 imb100top-1 error (%): 53.6 -> 55.0Hurt
pair by confusion matrix instead of OT (ablation)ERM + OTmix · CIFAR-LT-100 imb100top-1 error (%): 53.6 -> 57.1Hurt

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