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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add MCM module (ablation) | MambaML · Pascal VOC 2007 | mAP: 94.6 -> 94.8 | Improved |
| add MSDM module (ablation) | MambaML · Pascal VOC 2007 | mAP: 94.6 -> 94.8 | Improved |
| add MCM module (ablation) | MambaML · MS-COCO 2014 (448x448) | mAP: 85.2 -> 85.4 | Improved |
| add MSDM module (ablation) | MambaML · MS-COCO 2014 (448x448) | mAP: 85.2 -> 85.5 | Improved |
| add MCM module (ablation) | MambaML · NUS-WIDE | mAP: 65.2 -> 65.5 | Improved |
| add MSDM module (ablation) | MambaML · NUS-WIDE | mAP: 65.2 -> 65.6 | Improved |
| add both MCM and MSDM (ablation) | MambaML · MS-COCO 2014 (448x448) | mAP: 85.2 -> 85.7 | Improved |
| add both MCM and MSDM (ablation) | MambaML · NUS-WIDE | mAP: 65.2 -> 65.9 | Improved |
| increase decoder layers (ablation) | MambaML decoder · VOC/COCO/NUS-WIDE | mAP | Hurt |
| increase Mamba hidden states (ablation) | MambaML decoder · VOC/COCO/NUS-WIDE | mAP | No clear effect |
| raise input resolution from 448 to 576 | MambaML · MS-COCO 2014 | mAP: 85.7 -> 86.7 | Improved |
| MambaML vs Q2L | MambaML · NUS-WIDE | mAP: 65.0 -> 65.9 | Improved |
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.
- Prototype-based Causal Intervention for Multi-Label Image Classification (CVPR 2026 · better on 2 of 2 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
- In Pursuit of Causal Label Correlations for Multi-label Image Recognition (NeurIPS 2024 · similarity 0.87)
- Vision Mamba Mender (NeurIPS 2024 · similarity 0.86)
- MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025 · similarity 0.86)
- Mamba-Adaptor: State Space Model Adaptor for Visual Recognition (CVPR 2025 · similarity 0.86)
- Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning (CVPR 2025 · similarity 0.86)
- Counterfactual Reasoning for Multi-Label Image Classification via Patching-Based Training (ICML 2024 · similarity 0.85)
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.
