AI Paper Atlas

Research map / Continual learning / Class-incremental

TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery

Yanan Wu, Yuhan Yan, Tailai Chen, Zhixiang Chi, ZiZhang Wu, Yi Jin, Yang Wang, Zhenbo Li

CVPR 2026 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 2 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 margin-aware logit calibration (MLC) in offline training (ablation)TALON baseline · Stanford Cars (All)accuracy: 47.8 -> 49.0Improved
add MLC (ablation)TALON baseline · CUB-200-2011 (All)accuracy: 44.5 -> 45.7Improved
add semantic-aware prototype update (TTA-P) on top of MLC (ablation)TALON · Stanford Cars (All)accuracy: 49.0 -> 52.7Improved
add encoder adaptation (TTA-M) alone without MLC (ablation)TALON baseline · CUB-200-2011 (All)accuracy: 44.5 -> 44.5No clear effect
add encoder adaptation (TTA-M) on top of MLC (ablation)TALON · Stanford Cars (All)accuracy: 49.0 -> 52.1Improved
add both prototype and encoder adaptation on top of MLC (full TALON) (ablation)TALON · Stanford Cars (All)accuracy: 52.7 -> 53.5Improved
add both prototype and encoder adaptation on top of MLC (full TALON) (ablation)TALON · CUB-200-2011 (All)accuracy: 46.7 -> 45.5Hurt
replace TALON adaptation with TENT (ablation)baseline+MLC · Stanford Cars (All)accuracy: 49.0 -> 48.1Hurt
replace TALON adaptation with OSTTA (ablation)baseline+MLC · Stanford Cars (All)accuracy: 49.0 -> 47.2Hurt
use hash-free continuous prototypes instead of hash codes (vs PHE-64bit)OCD · CUB-200-2011 (Strict-Hungarian)estimated number of classes (true 200): 493 -> 153Improved
use hash-free continuous prototypes instead of hash codes (vs SMILE-64bit)OCD · Stanford Cars (Strict-Hungarian)estimated number of classes (true 196): 4788 -> 299Improved
use margin-aware logit calibration to shrink sample-to-prototype angle (ablation)baseline features · Oxford Petsmean angle to class prototype (degrees): 64.55 -> 35.83Improved

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