AI Paper Atlas

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

ACLS: Adaptive and Conditional Label Smoothing for Network Calibration

Hyekang Park, Jongyoun Noh, Youngmin Oh, Donghyeon Baek, Bumsub Ham

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 26 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 ACLS adaptive smoothing function only instead of MDCA adaptive regularization (ablation)ACLS · Tiny-ImageNet, ResNet-50ECE (%): 2.77 -> 1.54Improved
use ACLS indicator function only instead of MbLS (ablation)ACLS · Tiny-ImageNet, ResNet-50ECE (%): 1.64 -> 1.32Improved
combine adaptive smoothing and conditional indicator (ablation)ACLS · Tiny-ImageNet, ResNet-50ECE (%): 1.32 -> 1.05Improved
use margin condition instead of ranking condition (ablation)ACLS · Tiny-ImageNet, ResNet-50ECE (%): 1.48 -> 1.05Improved
use margin condition instead of ranking condition (ablation)CRL · Tiny-ImageNet, ResNet-50ECE (%): 1.65 -> 1.47Improved
ACLS loss versus CEResNet-50 · ImageNet valECE (%): 9.10 -> 1.02Improved
ACLS versus MbLS on segmentation accuracyDeepLabV3 ResNet-50 · PASCAL VOC valmIoU: 71.20 -> 70.63Hurt
ACLS versus label smoothing on Tiny-ImageNet accuracyResNet-50 · Tiny-ImageNet valtop-1 accuracy: 65.78 -> 64.84Hurt
ACLS regulation of top logit can flip predictionsACLS · Tiny-ImageNetsamples with altered prediction: 0.29% of samplesHurt

Later papers that compared with this method

1 later accepted paper reports ACLS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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