AI Paper Atlas

Research map / Continual learning / Class-incremental

Feature Decomposition-Recomposition in Large Vision-Language Model for Few-Shot Class-Incremental Learning

Zongyao Xue, Meina Kan, Shiguang Shan, Xilin Chen

ICCV 2025 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 1 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 holistic prototype calibration with similar base prototypes (ablation)Prototypical Network on CLIP · CUB200-1-shotNAcc: 19.86 -> 31.56Improved
replace holistic calibration with fine-grained keyword-segment recomposition (ablation)FDR · CUB200-1-shotNAcc: 31.56 -> 38.40Improved
ground keyword segments with CLIP attention and value matrices instead of random segments (ablation)FDR · CUB200-1-shotNAcc: 32.08 -> 38.40Improved
use attention-based keyword grounding instead of naive embedding product (ablation)FDR · CUB200-1-shotNAcc: 36.25 -> 38.40Improved
increase segment size q to 200 or 512 (ablation)FDR · CUB200-1-shotNAccHurt
increase number of base segments r beyond 50 (ablation)FDR · CUB200-1-shotNAccNo clear effect
set calibration ratio alpha to 0.5 versus lower or higher (ablation)FDR · CUB200-1-shotNAccImproved
apply FDR calibration instead of TEEN on frozen CLIPCUB200 5-shot · CUB200-5-shotNAcc: 58.83 -> 62.79Improved
apply FDR in trained setting versus EASE on miniImageNetFDR · miniImageNet (5-shot)AvgAcc across sessions: 89.2 vs 93.9 for EASEHurt

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