AI Paper Atlas

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

ECCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 63 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
use Mamba Twister fusion instead of cross-attention conditioning in Mamba (ablation)ReMamber · RefCOCO val (256 res)mIoU: 65.3 -> 71.6Improved
use Mamba Twister instead of in-context conditioning (prepend text tokens) (ablation)ReMamber · RefCOCO val (256 res)mIoU: 69.1 -> 71.6Improved
use Mamba Twister instead of norm adaptation (FiLM) (ablation)ReMamber · RefCOCO val (256 res)mIoU: 70.2 -> 71.6Improved
add Spatial Scan to Channel Scan in the twisting mechanism (ablation)ReMamber · RefCOCO val (256 res)mIoU: 62.3 -> 71.6Improved
add Channel Scan to Spatial Scan (ablation)ReMamber · RefCOCO val (256 res)mIoU: 70.0 -> 71.6Improved
order Channel-Spatial instead of Spatial-Channel or Parallel (ablation)ReMamber · RefCOCO val (256 res)mIoU: 71.4 -> 71.6No clear effect
add local interaction to global-only hybrid cube (ablation)ReMamber · RefCOCO val (256 res)mIoU: 69.1 -> 71.6Improved
add global text interaction to local-only hybrid cube (ablation)ReMamber · RefCOCO val (256 res)mIoU: 69.9 -> 71.6Improved
use Mamba-B ReMamber instead of Swin-B LAVTreferring image segmentation · RefCOCO valoIoU: 72.73 -> 74.54Improved

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