Research map / Vision-language and multimodal / Cross-modal learning
ReMamber: Referring Image Segmentation with Mamba Twister
Yuhuan Yang, Chaofan Ma, Jiangchao Yao, Zhun Zhong, Ya Zhang, Yanfeng 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 |
|---|---|---|---|
| use Mamba Twister fusion instead of cross-attention conditioning in Mamba (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 65.3 -> 71.6 | Improved |
| use Mamba Twister instead of in-context conditioning (prepend text tokens) (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 69.1 -> 71.6 | Improved |
| use Mamba Twister instead of norm adaptation (FiLM) (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 70.2 -> 71.6 | Improved |
| add Spatial Scan to Channel Scan in the twisting mechanism (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 62.3 -> 71.6 | Improved |
| add Channel Scan to Spatial Scan (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 70.0 -> 71.6 | Improved |
| order Channel-Spatial instead of Spatial-Channel or Parallel (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 71.4 -> 71.6 | No clear effect |
| add local interaction to global-only hybrid cube (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 69.1 -> 71.6 | Improved |
| add global text interaction to local-only hybrid cube (ablation) | ReMamber · RefCOCO val (256 res) | mIoU: 69.9 -> 71.6 | Improved |
| use Mamba-B ReMamber instead of Swin-B LAVT | referring image segmentation · RefCOCO val | oIoU: 72.73 -> 74.54 | Improved |
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.
- LAVT — LAVT: Language-Aware Vision Transformer for Referring Image Segmentation (CVPR 2022) · better on 4 of 4 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
- Mask Grounding for Referring Image Segmentation (CVPR 2024 · similarity 0.87)
- LQMFormer: Language-aware Query Mask Transformer for Referring Image Segmentation (CVPR 2024 · similarity 0.86)
- Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation (CVPR 2025 · similarity 0.86)
- SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation (NeurIPS 2025 · similarity 0.86)
- Prompt-Driven Referring Image Segmentation with Instance Contrasting (CVPR 2024 · similarity 0.86)
- Mamba-Reg: Vision Mamba Also Needs Registers (CVPR 2025 · similarity 0.86)
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.
