AI Paper Atlas

Research map / Continual learning / Class-incremental

Random Anchors with Low-rank Decorrelated Learning: A Minimalist Pipeline for Class-Incremental Medical Image Classification

Xinyao Wu, Zhe Xu, Raymond Kai-yu Tong

ICLR 2026 · Continual learning › Class-incremental · approach: Exemplar-efficient class-incremental learning

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 first-stage adaptation (ablation)RA-LDL (with LRP) · COVID (CT&X-rays)AccLast (%): 90.30 -> 88.04Hurt
add first-stage adaptation (ablation)RA-LDL (with LRP) · Skin8AccLast (%): 60.85 -> 62.49Improved
add first-stage adaptation (ablation)RA-LDL (with LRP) · MedMNIST-SubAccLast (%): 70.29 -> 70.60No clear effect
add LRP residual to random anchor (without first-stage adaptation) (ablation)RA-DL · COVID (CT&X-rays)AccLast (%): 86.94 -> 90.30Improved
add LRP residual to random anchor (without first-stage adaptation) (ablation)RA-DL · Skin8AccLast (%): 61.26 -> 60.85Hurt
add LRP residual to random anchor (without first-stage adaptation) (ablation)RA-DL · MedMNIST-SubAccLast (%): 69.32 -> 70.29Improved
add analytical decorrelated classifier instead of prototype classifier (ablation)ViT-B/16-IN21K classifier · MedMNIST-Subaccuracy: 50.45 -> 66.44Improved
add analytical decorrelated classifier instead of prototype classifier (ablation)ViT-B/16-IN21K classifier · IN-Aaccuracy: 48.39 -> 54.18Improved
use standard Gaussian instead of Kaiming uniform for random matrix (ablation)RA-LDL w/o first-stage adaptation · BloodAccLast (%): 83.71 -> 97.74Improved
use standard Gaussian instead of Kaiming uniform with parameter 5 (ablation)RA-LDL w/o first-stage adaptation · BloodAccLast (%): 19.31 -> 97.74Improved
increase random projection dimension from d0 to 5d0 (ablation)RA-LDL w/o first-stage adaptation · CIFARAccLast (%): 85.61 -> 87.63Improved
increase random projection dimension from d0 to 5d0 (ablation)RA-LDL w/o first-stage adaptation · Skin8AccLast (%): 56.74 -> 60.85Improved

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