AI Paper Atlas

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

Local and Global Logit Adjustments for Long-Tailed Learning

Yingfan Tao, Jingna Sun, Hao Yang, Li Chen, Xu Wang, Wenming Yang, Daniel Du, Min Zheng

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Classifier rebalancing and margin losses · 38 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
replace BALMS logit adjustment with Class-aware Logit Adjustment (CLA) (ablation)3-expert model · CIFAR-100-LT (IF=100)top-1 accuracy (%): 55.24 -> 56.53Improved
add AAW loss to BALMS (ablation)3-expert BALMS · CIFAR-100-LT (IF=100)top-1 accuracy (%): 55.24 -> 56.51Improved
add AAW loss to CLA (ablation)CLA 3-expert model · CIFAR-100-LT (IF=100)top-1 accuracy (%): 56.53 -> 57.15Improved
use RandAugment (ablation)Softmax baseline · CIFAR-100-LT (IF=100)top-1 accuracy (%): 41.88 -> 47.97Improved
use RandAugment (ablation)LGLA (GC) · CIFAR-100-LT (IF=100)top-1 accuracy (%): 49.58 -> 57.15Improved
increase number of experts beyond 3 (ablation)LGLA · CIFAR-100-LT (IF=100)top-1 accuracy (%)No clear effect
increase number of experts from 2 to 3 (ablation)LGLA · CIFAR-100-LT (IF=100)top-1 accuracy (%)Improved
use group convolution instead of independent convolution for experts (ablation)LGLA · CIFAR-100-LT (IF=100)top-1 accuracy (%): 56.5 -> 57.2Improved
raise fusion weight of an LLA expert (ablation)4-expert LGLA · CIFAR-100-LT (IF=100)top-1 accuracy on matching splitImproved
LGLA vs ResLT/NCL on Many-shot classesLGLA · iNaturalist 2018 (Many)top-1 accuracy (%): 73.0 -> 69.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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