AI Paper Atlas

Research map / Continual learning / Online and replay-based

CLR: Channel-wise Lightweight Reprogramming for Continual Learning

Yunhao Ge, Yuecheng Li, Shuo Ni, Jiaping Zhao, Ming-Hsuan Yang, Laurent Itti

ICCV 2023 · Continual learning › Online and replay-based · approach: Unified and unsupervised continual frameworks · 12 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 channel-wise lightweight reprogramming with frozen backbone versus best prior dynamic-network method CCLLCLR · 53-dataset (task-incremental)average accuracy: 78.3 % -> 86.05 %Improved
use task-specific CLR layers with a shared immutable backbone to isolate parametersCLR · 53-dataset (task 1 accuracy over time)forgettingImproved
pretrain backbone on Pascal VOC instead of ImageNet-1k (ablation)CLR · 53-dataset (task-incremental)average accuracy: 86.05 % -> 82.49 %Hurt
use self-supervised DINO or SwAV backbone instead of supervised ImageNet-1k (ablation)CLR · 53-dataset (task-incremental)average accuracy: 86.05 % -> 85.77 % (DINO), 85.12 % (SwAV)No clear effect
apply CLR layers to all conv kernels including 1x1 (CLR-Full) (ablation)CLR · 53-dataset (task-incremental)average accuracy: 86.05 -> 85.85No clear effect
learn weighted mix of original and reprogrammed feature maps (CLR-mixed) (ablation)CLR · 53-dataset (task-incremental)average accuracy: 86.05 -> 86.25Improved
initialize CLR kernels as identity transformationCLR · 53-datasettraining efficiency and performanceImproved
use CLR instead of Head2Toe for transfer learningCLR · 53-dataset (transfer learning)average accuracy: almost 5% average improvementImproved
use replay buffer (ER) instead of plain SGD fine-tuningSGD baseline · 53-dataset (task-incremental)average accuracy: 16.71 % -> 53.13 %Improved
apply CLR on incremental CIFAR-100 versus CCLLCLR · Incremental CIFAR-100 (10 tasks)average accuracy: 85% -> 94.2%Improved

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