AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Subspace Alignment for CLIP-based Continual Learning via Canonical Correlation Analysis

Huan Zhang, Shuyu Dong, Yujin Zheng, Dingwen Wang, Shenghua Fan, Fan Lyu

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Fine-grained improvements to CLIP

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 CCA subspace projection (ablation)Continual-CLIP · CIFAR-100last accuracy: 66.7 -> 76.5Improved
add Random Fourier Projection to CCA (ablation)CCA-CL (no FTT) · CIFAR-100last accuracy: 76.5 -> 81.0Improved
add first-task fine-tuning (ablation)CCA-CL · CIFAR-100last accuracy: 81.0 -> 83.0Improved
lower energy threshold from 0.99 to 0.9 (ablation)CCA-CL (no FTT) · CIFAR-100last accuracy: 81.0 -> 76.5Hurt
raise energy threshold from 0.99 to 1 (ablation)CCA-CL (no FTT) · CIFAR-100last accuracy: 81.0 -> 80.8No clear effect
widen RFP from 6144 to 10240 (ablation)CCA-CL (no FTT) · CIFAR-100last accuracy: 81.0 -> 80.2; memory 6.3 -> 11.9 GHurt
narrow RFP from 6144 to 2048 (ablation)CCA-CL (no FTT) · CIFAR-100last accuracy: 81.0 -> 79.7Hurt
use CCA-CL instead of RAPF for efficiencyCIFAR-100 training · CIFAR-100learning time (minutes): 13.9 -> 5.8Improved
remove first-task training (ablation)CCA-CL · CIFAR-100learning time (minutes): 5.8 -> 3.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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