AI Paper Atlas

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

Model Calibration in Dense Classification with Adaptive Label Perturbation

Jiawei Liu, Changkun Ye, Shan Wang, Ruikai Cui, Jing Zhang, Kaihao Zhang, Nick Barnes

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Confidence calibration objectives · 5 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
make label perturbation probability adaptive per training image (ASLP_MC) instead of static SLP (ablation)Stochastic Label Perturbation · DUTS-TEECE (%): 2.21 -> 1.40Improved
add stochastic label perturbation to baseline (ablation)baseline SOD model · DUTS-TEECE (%): 3.48 -> 2.21Improved
use calibration regulariser (ASLP_MC) instead of accuracy regulariser (ASLP_MEI) (ablation)ASLP · DUTS-TEECE (%): 27.9 -> 1.40Improved
use accuracy regulariser (ASLP_MEI) instead of calibration regulariser (ablation)ASLP · Describable Textures (OOD)ECE (%): 18.31 -> 13.43Improved
apply ASLP_MC instead of AdaFocalAdaFocal · Describable Textures (OOD)ECE (%): 27.55 -> 18.31Improved
apply temperature scalingbaseline SOD model · Describable Textures (OOD)ECE (%): 52.36 -> 51.95No clear effect
make label smoothing factor adaptive per image (ALS) instead of static LS (ablation)Label Smoothing · DUTS-TEECE (%): 2.20 -> 1.46Improved
add Gaussian noise (dynamic moderation) to moderation perturbation (ablation)ASLP_MC · DUTS-TEECE (%): 1.47 -> 1.64Hurt
add dynamic Gaussian noise to moderation perturbation (ablation)ASLP_MC · SOD datasetECE (%): 5.63 -> 4.14Improved
increase static label perturbation probability beyond a small value (ablation)SLP · SOD testing datasetsECEHurt
set regularisation strength lambda very high (ablation)ASLP_MC · SODcalibrationHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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