AI Paper Atlas

Research map / Detection and segmentation / CNN features

MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders

Baijiong Lin, Weisen Jiang, Pengguang Chen, Yu Zhang, Shu Liu, Yingcong Chen

ECCV 2024 · Detection and segmentation › CNN features · approach: Vision state space models · 30 citations (OpenAlex)

Read the paper

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 Swin Transformer decoder blocks with STM blocks (ablation)multi-task decoder · NYUDv2Delta_m (%): -1.87 -> +1.84Improved
increase STM blocks from two to three (ablation)MTMamba · NYUDv2Delta_m (%): +1.84 -> +1.55No clear effect
add cross-task Mamba (CTM) block (ablation)MTMamba · NYUDv2Delta_m (%): +1.84 -> +2.38Improved
replace Mamba feature extractor (MFE) with window attention (ablation)MTMamba · NYUDv2Delta_m (%): +2.38 -> -0.79Hurt
replace linear gate with attention-based gate (ablation)MTMamba · NYUDv2Delta_m (%): +2.38 -> +2.08No clear effect
use adaptive gate in CTM instead of fixed g^t=0 or g^t=1 (ablation)MTMamba · NYUDv2Delta_m (%): +1.77 / +1.76 -> +2.38Improved
scale Swin encoder from Tiny to Large (ablation)MTMamba · NYUDv2Semseg mIoU: 49.25 -> 55.82Improved
use MTMamba instead of best Transformer decoders on PASCAL-Contextmulti-task decoder · PASCAL-ContextSaliency maxF: 84.81 -> 84.14 (saliency)Mixed
use MTMamba instead of InvPT on PASCAL-Contextmulti-task decoder · PASCAL-ContextParsing mIoU: 67.61 -> 72.62Improved

Later papers that compared with this method

1 later accepted paper reports MTMamba as a baseline in their results tables; 0 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