AI Paper Atlas

Research map / Continual learning / Class-incremental

Consistency-Driven Calibration and Matching for Few-Shot Class Incremental Learning

Qinzhe Wang, Zixuan Chen, Keke Huang, Xiu Su, Chunhua Yang, Chang Xu

ICLR 2026 · 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 memory-aware prototype calibration (MPC) (ablation)ConCM (projector only) · mini-ImageNetAHM: 47.83 -> 52.35Improved
add dynamic structure matching (DSM) (ablation)ConCM (projector only) · mini-ImageNetAHM: 47.83 -> 56.79Improved
add both MPC and DSM (ablation)ConCM (projector only) · mini-ImageNetAHM: 47.83 -> 59.78Improved
add MPC on top of DSM (ablation)ConCM · CIFAR100AHM: 56.96 -> 59.05Improved
add MPC on top of DSM (ablation)ConCM · CUB200AHM: 60.19 -> 62.20Improved
add fine-tuned projector to frozen backbone (ablation)ConCM baseline · mini-ImageNetAHM: 22.00 -> 47.83Improved
replace cross-entropy with matching loss (ablation)ConCM · mini-ImageNetAHM: 47.83 -> 55.28Improved
add contrastive loss with anchor to matching loss (ablation)ConCM · mini-ImageNetAHM: 55.28 -> 59.78Improved
use anchor contrastive loss instead of general SCL loss (ablation)ConCM · mini-ImageNetAHM: 59.42 -> 59.78Improved
use DSM only when class names absent from WordNet (no MPC)ConCM w/o MPC vs NC-FSCIL · mini-ImageNetAHM: 52.62 -> 56.79Improved
ConCM versus best baseline OrCoConCM · CIFAR100final-session accuracy: 57.51 -> 58.33Improved
ConCM versus OrCo on first incremental sessionConCM · CIFAR100session-1 harmonic mean: 72.11 -> 72.27No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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