AI Paper Atlas

Research map / Continual learning / Class-incremental

Palimpsest: Reconciling the CISS Trilemma for Incremental Nuclei Segmentation

Jiajia Li, Huisi Wu

AAAI 2026 · Continual learning › Class-incremental · approach: Unknown-class mining for incremental segmentation · 1 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 Adaptive Residual Shading (logit-space background decoupling) (ablation)PCS (no SCR) · MoNuSAC 2-1Mean Dice: 44.54 -> 68.33Improved
add Similarity-Aware Centroid Recalibration (ablation)PCS + ARS · MoNuSAC 2-1Mean Dice: 68.33 -> 71.57Improved
merge adapters via PCS alone (ablation)baseline adapter · MoNuSAC 2-1Mean Dice: 46.94 -> 44.54Hurt
add margin-based LARS (ablation)Lnew only · MoNuSAC 2-1Mean Dice: 44.54 -> 65.94Improved
add foreground feature consistency loss LFFC (ablation)Lnew + LARS · MoNuSAC 2-1Mean Dice: 65.94 -> 71.57Improved
replace uniform recalibration with similarity-aware SCR (ablation)Uniform recalibration · MoNuSAC 2-1Mean Dice: 62.76 -> 71.57Improved
use no calibration vs SCR (ablation)No calibration · MoNuSAC 2-1Mean Dice: 51.32 -> 71.57Improved
compare SCR with naive exemplar replay (ablation)Naive Replay · MoNuSAC 2-1Mean Dice: 72.89 vs 71.57No clear effect
Palimpsest vs InSegInSeg · MoNuSAC 1-1 (4 steps)Mean Dice: 69.42 -> 71.28Improved
Palimpsest vs InSegInSeg · CoNSeP 2-1Mean Dice: 71.08 -> 71.84Improved
Palimpsest vs InSeg on new classesInSeg · MoNuSAC 3-1New-class Dice: 77.81 -> 77.75No clear effect

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