AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

MambaML: Exploring State Space Models for Multi-Label Image Classification

Xuelin Zhu, Jian Liu, Jiuxin Cao, Bing Wang

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Partial and multi-label learning · 4 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 MCM module (ablation)MambaML · Pascal VOC 2007mAP: 94.6 -> 94.8Improved
add MSDM module (ablation)MambaML · Pascal VOC 2007mAP: 94.6 -> 94.8Improved
add MCM module (ablation)MambaML · MS-COCO 2014 (448x448)mAP: 85.2 -> 85.4Improved
add MSDM module (ablation)MambaML · MS-COCO 2014 (448x448)mAP: 85.2 -> 85.5Improved
add MCM module (ablation)MambaML · NUS-WIDEmAP: 65.2 -> 65.5Improved
add MSDM module (ablation)MambaML · NUS-WIDEmAP: 65.2 -> 65.6Improved
add both MCM and MSDM (ablation)MambaML · MS-COCO 2014 (448x448)mAP: 85.2 -> 85.7Improved
add both MCM and MSDM (ablation)MambaML · NUS-WIDEmAP: 65.2 -> 65.9Improved
increase decoder layers (ablation)MambaML decoder · VOC/COCO/NUS-WIDEmAPHurt
increase Mamba hidden states (ablation)MambaML decoder · VOC/COCO/NUS-WIDEmAPNo clear effect
raise input resolution from 448 to 576MambaML · MS-COCO 2014mAP: 85.7 -> 86.7Improved
MambaML vs Q2LMambaML · NUS-WIDEmAP: 65.0 -> 65.9Improved

Later papers that compared with this method

1 later accepted paper reports MambaML 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