AI Paper Atlas

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

Invariant Feature Learning for Generalized Long-Tailed Classification

Kaihua Tang, Mingyuan Tao, Jiaxin Qi, Zhenguang Liu, Hanwang Zhang

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 53 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 IFL (two environments with invariant metric loss) (ablation)ResNeXt-50 baseline · ImageNet-GLT GLT protocolaccuracy: 34.75 -> 37.96Improved
add IFLResNeXt-50 baseline · ImageNet-GLT CLT protocolaccuracy: 42.52 -> 45.97Improved
add IFLResNeXt-50 baseline · ImageNet-GLT ALT protocolaccuracy: 41.73 -> 45.89Improved
add IFLRandAug · ImageNet-GLT GLT protocolaccuracy: 38.24 -> 44.90Improved
add IFLRIDE · ImageNet-GLT GLT protocolaccuracy: 43.00 -> 45.64Improved
add IFLcRT · ImageNet-GLT ALT protocolaccuracy: 41.59 -> 45.47Improved
add IFLRIDE · MSCOCO-GLT ALT protocolaccuracy: 58.90 -> 58.93No clear effect
add IFLLDAM · ImageNet-GLT ALT protocolaccuracy: 42.66 -> 44.86 (BLSoftmax + IFL)Improved
use vanilla center loss with a single environment (ablation)ResNeXt-50 baseline · ImageNet-GLT GLT protocolaccuracy: 34.75 -> 32.82Hurt
use original IRM loss instead of IFL loss (ablation)ResNeXt-50 · ImageNet-GLT GLT protocolaccuracy: 37.96 -> 36.03Hurt
increase environments from 2 to 3 (ablation)IFL · ImageNet-GLT GLT protocolaccuracy: 37.96 -> 38.32No clear effect
replace CE with focal loss (ablation)ResNeXt-50 baseline · ImageNet-GLT GLT protocolaccuracy: 34.75 -> 32.52Hurt

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