AI Paper Atlas

Research map / Continual learning / Class-incremental

Mamba-FSCIL: Dynamic Adaptation With Selective State Space Model for Few-Shot Class Incremental Learning

Xiaojie Li, Yibo Yang, Jianlong Wu, Yue Yu, Ming-Hsuan Yang, Liqiang Nie, Min Zhang

TPAMI 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
replace the 3-layer MLP projector with a single selective SSM projector (ablation)Mamba-FSCIL baseline · CIFAR-100AVG accuracy: 63.51 -> 66.90Improved
replace the 3-layer MLP projector with a single selective SSM projector (ablation)Mamba-FSCIL baseline · CIFAR-100performance drop: 33.55 -> 27.57Improved
replace the 3-layer MLP projector with a single selective SSM projector (ablation)Mamba-FSCIL baseline · miniImageNetAVG accuracy: 63.09 -> 66.79Improved
split into dual (frozen base + incremental) selective SSM branches (ablation)single selective SSM projector · miniImageNetAVG accuracy: 66.79 -> 69.20Improved
split into dual (frozen base + incremental) selective SSM branches (ablation)single selective SSM projector · miniImageNetperformance drop: 29.11 -> 26.01Improved
split into dual (frozen base + incremental) selective SSM branches (ablation)single selective SSM projector · CIFAR-100AVG accuracy: 66.90 -> 67.52Improved
add class-sensitive selective scan (suppression + separation losses) (ablation)dual selective SSM projector · miniImageNetsession 8 accuracy: 58.92 -> 59.36Improved
add class-sensitive selective scan (suppression + separation losses) (ablation)dual selective SSM projector · CIFAR-100session 8 accuracy: 56.71 -> 57.51Improved
add class-sensitive selective scan (suppression + separation losses) (ablation)dual selective SSM projector · CIFAR-100performance drop: 26.09 -> 25.29Improved
freeze identity and base SSM branches in incremental sessions (ablation)Mamba-FSCIL (ResNet-12) · miniImageNetaccuracyImproved
increase scan paths K from 1 to 4 (ablation)Mamba-FSCIL · CIFAR-100session 8 accuracy: 55.94 -> 57.51Improved
increase scan paths K from 1 to 4 (ablation)Mamba-FSCIL · CIFAR-100AVG accuracy: 67.23 -> 68.14Improved

Later papers that compared with this method

1 later accepted paper reports Mamba-FSCIL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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