AI Paper Atlas

Research map / Continual learning / Class-incremental

Quantized Residuals to Continuous Prompts for Few-Shot Class Incremental Learning in Vision-Language Models

Abhishek Kumar Sinha, Nitant Dube, Soma Biswas

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 DSQ rotation (ablation)QR-Prompt · CUB200, final sessionaccuracy (%): 78.46 -> 80.68Improved
add HPE cross-subspace attention (ablation)QR-Prompt · CUB200, final sessionaccuracy (%): 78.42 -> 80.68Improved
add Prompt Composer (ablation)QR-Prompt · CUB200, final sessionaccuracy (%): 80.07 -> 80.68Improved
use visual-textual residuals instead of visual features (ablation)QR-Prompt · CUB200, final sessionaccuracy (%): 78.59 -> 80.68Improved
use QR-Prompt instead of BiMCCLIP-based FSCIL · CUB200average accuracy (%): 80.49 -> 82.12Improved
use QR-Prompt instead of BiMCCLIP-based FSCIL · CIFAR100average accuracy (%): 78.45 -> 79.32Improved
use QR-Prompt instead of VQPromptprompt-based FSCIL · CIFAR100average accuracy (%): 82.29 -> 79.32Hurt
use QR-Prompt instead of VQPromptprompt-based FSCIL · miniImageNetperformance drop (%): 1.41 -> 1.64Hurt
increase number of subspaces M from 8 to 32 (K=32) (ablation)DSQ · CUB200average accuracyImproved
increase M beyond 32 (K=32) (ablation)DSQ · CUB200average accuracyHurt
increase codewords per subspace K (M=32) (ablation)DSQ · CUB200average accuracyNo clear effect
use moderate lambda in [0.1, 0.2] versus very small or large (ablation)DSQ · CUB200average accuracyMixed

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