AI Paper Atlas

Research map / Continual learning / Class-incremental

HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning

Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee, JiHyun Kim, Soojin Jang, YoungBin Kim

CVPR 2026 · Continual learning › Class-incremental · approach: Few-shot class-incremental prototypes · 0 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
use dynamic weighted fusion instead of cosine similarity alone (ablation)HyCal · High-Scale Domain ImbalanceS_CDE: 51.29 -> 53.70Improved
use dynamic weighted fusion instead of Mahalanobis alone (ablation)HyCal · High-Scale Domain ImbalanceS_CDE: 53.50 -> 53.70Improved
use dynamic weighting instead of plain average of the two metrics (ablation)HyCal · Cross-Scale ImbalanceS_CDE: 58.24 -> 59.24Improved
add Mahalanobis distance to cosine similarity under balanced domains (ablation)HyCal · Balanced-in-Class DomainS_CDE: 56.82 -> 60.92Improved
sum image-text embeddings instead of concatenating (ablation)HyCal · High-Scale Domain ImbalanceS_CDE: 53.39 -> 53.70Improved
sum image-text embeddings instead of concatenating (ablation)HyCal · Balanced-in-Class DomainS_CDE: 60.70 -> 60.92Improved
HyCal versus second-best training-free method (KLDA) under high-scale imbalanceHyCal · High-Scale Domain ImbalanceAverage accuracy: over 4.5%pImproved
HyCal versus KLDA under cross-scale imbalanceHyCal · Cross-Scale ImbalanceS_CDE: 59.61 -> 59.24Hurt
increase shots from 5 to 20HyCal · FSCILLast accuracy: 60.82 -> 70.67Improved
use OpenCLIP ViT-B/16 DataComp-1B backboneHyCal · High-Scale Domain ImbalanceLast accuracy: 68.88 vs 66.20Improved
random domain order (ablation)HyCal · XD-VSCILaccuracyNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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