AI Paper Atlas

Research map / Detection and segmentation / CNN features

Rethinking Model Calibration through Spectral Entropy Regularization in Medical Image Segmentation

Kun Cheng, Yukun Zhang, William Henry Nailon, Tonggang Zhao

ICLR 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation

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 temporal smoothing of the spectral profile to spectral entropy regularization (ablation)LCE w/ LSpectral · BraTS2020ECE: 0.0065 -> 0.0015Improved
add temporal smoothing of the spectral profile to spectral entropy regularization (ablation)LCE w/ LSpectral · FLARE2021ECE: 0.0170 -> 0.0008Improved
add temporal smoothing of the spectral profile (ablation)LCE w/ LSpectral · FLARE2021HD95: 6.15 -> 4.55Improved
add temporal smoothing of the spectral profile (ablation)LCE w/ LSpectral · BraTS2020DSC: 0.870 -> 0.872Improved
add unsmoothed spectral entropy regularization to CE (ablation)U-Net CE baseline · BraTS2020ECE: 0.0091 -> 0.0065Improved
add unsmoothed spectral entropy regularization to CE (ablation)U-Net CE baseline · FLARE2021ECE: 0.0255 -> 0.0170Improved
use spectral entropy regularization instead of CE aloneU-Net · ACDCECE (x10^-3): 32.5 -> 2.1Improved
replace CE with Focal LossU-Net · FLARE2021DSC (%): 91.5 -> 87.7Hurt
increase regularization weight lambda to 0.100 (ablation)LCE w/ LSpectral · BraTS2020DSC: 0.872 -> 0.865Hurt
reduce lambda to 0.001 (ablation)LCE w/ LSpectral · BraTS2020ECE: 0.0015 -> 0.0045Hurt
enlarge smoothing window W to 100 (ablation)LCE w/ LSpectral · BraTS2020ECE: 0.0015 -> 0.0022Hurt
shrink smoothing window W to 10 (ablation)LCE w/ LSpectral · BraTS2020ECE: 0.0015 -> 0.0025Hurt

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