AI Paper Atlas

Research map / Continual learning / Domain and prompt-based

Continual Segmentation under Joint Nonstationarity

Prashant Pandey, Himanshu Kumar, Devineni Sri Venkatraya Chowdary, Brejesh Lall

ICML 2026 · Continual learning › Domain and prompt-based · approach: Domain-incremental learning with memory · 0 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 JASCL to U-NetU-Net · Med JASCL-Disjoint (session 1)Dice: 0.076 -> 0.460Improved
add JASCL to U-NetU-Net · Med JASCL-Disjoint (session 5)Dice: 0.042 -> 0.324Improved
add JASCL to MedFormerMedFormer · Med JASCL-Mixed (session 4)Dice: 0.067 -> 0.228Improved
add JASCL to SwinUNetrSwinUNetr · Med JASCL-Mixed (session 4)Dice: 0.082 -> 0.210Improved
add JASCL to SAMSAM ViT-B · Natural-JASCL (session 2)mIoU: 30.81 -> 31.22Improved
add JASCL with unlabeled data to GAPSGAPS · Semi-Supervised Natural-JASCL (session 3)mIoU: 14.45 -> 25.47Improved
add JASCL to MedFormer with unlabeled dataMedFormer · Med Semi-Supervised-JASCL (session 5)Dice: 0.040 -> 0.293Improved
add gradient adaptive stabilization (GAS) (ablation)JASCL (MedFormer) · Med JASCL-MixedDiceImproved
add prototype anchored supervision (PAS) (ablation)JASCL + GAPS · Semi-Supervised Natural-JASCLmIoUImproved
lower epsilon from 1e-6 to 1e-9 (ablation)JASCL (U-Net) · Med JASCL-Disjoint session 1Dice: 0.443 -> 0.482Mixed
raise noise variance from 1 to 10 (ablation)JASCL (U-Net) · Med JASCL-Disjoint session 1Dice: 0.460 -> 0.408Hurt
increase shots K from 3 to 5 (ablation)JASCL (U-Net) · Med JASCL-Disjoint session 1Dice: 0.414 -> 0.460Improved

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