AI Paper Atlas

Research map / Continual learning / Class-incremental

Revisiting Pool-based Prompt Learning for Few-shot Class-incremental Learning

Yongwei Jiang, Yixiong Zou, Yuhua Li, Ruixuan Li

ICCV 2025 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 3 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 basic VPT prompts to vanilla ViT (ablation)ViT · CUB-200 FSCILoverall accuracy: 61.66 -> 79.26Improved
add single local spatial prompt (LSP*) (ablation)VPT · CUB-200 FSCILoverall accuracy: 79.26 -> 79.49Improved
use a local spatial prompt pool instead of a single prompt (ablation)VPT+LSP · iNF200 FSCILoverall accuracy: 52.94 -> 56.87Improved
add global frequency-domain spatial prompting to local prompts (ablation)LGSP-Prompt · FGVCAircraft FSCILoverall accuracy: 21.58 -> 25.82Improved
combine LSP and GSP vs LSP only (ablation)LGSP-Prompt · FGVCAircraft base sessionbase accuracy: 28.27 -> 27.67Hurt
use larger kernel sizes (>11) in LSP (ablation)LSP · FSCILaccuracyHurt
vary frequency ring count in GSP (ablation)GSP · FSCILaccuracyNo clear effect
increase local prompt pool size (ablation)LSP · FSCILaccuracyImproved
use prompt pools (CODA-Prompt) vs non-prompt methods in FSCILCODA-Prompt · CUB-200 FSCILaverage accuracy: CODA-Prompt 74.63 vs TEEN 78.11Hurt

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