AI Paper Atlas

Research map / Continual learning / Online and replay-based

CHEEM: Continual Learning by Reuse, New, Adapt and Skip - A Hierarchical Exploration-Exploitation Approach

Chinmay Savadikar, Michelle Dai, Tianfu Wu

CVPR 2026 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks

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 architecture search (reuse/adapt/new/skip) over LoRA-CL (ablation)CHEEM · MTIL (DEiT-Tiny)average accuracy: 71.1 -> 74.5Improved
add architecture search over LoRA-CL (ablation)CHEEM · MTIL (ViT-Base)average accuracy: 84.7 -> 85.9Improved
use HEE sampling instead of uniform sampling in supernet training (ablation)CHEEM · MTIL (ViT-Base)% parameter increase: 5.89 -> 0.25Improved
use HEE sampling instead of uniform sampling in supernet training (ablation)CHEEM · MTIL (ViT-Base)average accuracy: 84.74 -> 85.88Improved
use HEE sampling instead of uniform sampling in supernet training (ablation)CHEEM · MTIL (DEiT-Tiny)average accuracy: 75.05 -> 74.51No clear effect
place CHEEM at attention projection instead of MLP Down (ablation)CHEEM · MTIL (ViT-Base)FLOPs: 62.31 -> 65.91Hurt
use DEiT-Tiny instead of ViT-Base for task ID inference (ablation)CHEEM lite · MTIL (ViT-Base)average accuracy: 85.9 -> 84.2No clear effect
use AlexNet instead of ViT-Base for task ID inference (ablation)CHEEM lite · MTIL (ViT-Base)average accuracy: 85.9 -> 79.9Hurt
add dynamic task-tailored backbone vs prompting baselines (S-Prompts)CHEEM · MTIL (DEiT-Tiny)average accuracy: 67.3 -> 74.5Improved
change task order of MTIL stream (ablation)CHEEM · MTIL (ViT-Base)average accuracy: 85.65, 84.74, 85.63No clear effect
use CLIP ViT-B/16 backboneCHEEM · VDD (CLIP ViT-B/16)average accuracy: LoRA-CL 85.8 vs CHEEM 84.5Mixed

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