AI Paper Atlas

Research map / Continual learning / Class-incremental

TAPE: Task-Adaptive Prototype Evolution in Audio-Language Models for Fully Few-shot Class-incremental Audio Classification

Yunlong Gao, Wenxin Liang, Guanglu Wang, Senqi Guan, Linlin Zong, Dongyu Zhang, Xinyue Liu

CVPR 2026 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes

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 Prototype Evolution to baseline (ablation)prototypical-network baseline · LBS-100Average Accuracy: 40.30 -> 83.54Improved
add Prototype Evolution to baseline (ablation)prototypical-network baseline · FSC-89Average Accuracy: 48.12 -> 67.88Improved
add Task-Adapter to baseline (ablation)prototypical-network baseline · LBS-100Performance Dropping rate: 61.94 -> 15.49Improved
add Task-Adapter to baseline (ablation)prototypical-network baseline · Nsynth-100Performance Dropping rate: 28.89 -> 5.83Improved
add Task-Adapter on top of Prototype Evolution (ablation)Prototype Evolution variant · FSC-89Performance Dropping rate: 21.19 -> 20.53Improved
add Prototype Evolution on top of Task-Adapter (ablation)Task-Adapter variant · LBS-100Average Accuracy: 82.20 -> 84.53Improved
use frozen CLAP encoder with prototypes instead of prompt tuning (TAPE vs PALM)PALM · Nsynth-100Average Accuracy: 51.65 -> 94.78Improved
zero-shot CLAP with class namesCLAP · LBS-100accuracy: about 10% average accuracyHurt

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