AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Multi-modal Segment Anything Model for Camouflaged Scene Segmentation

Guangyu Ren, Hengyan Liu, Michalis Lazarou, Tania Stathaki

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 10 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 BLIP caption language prompt (ablation)SAM baseline · CHAMELEONweighted F-measure: 0.666 -> 0.706Improved
add BLIP caption language prompt (ablation)SAM baseline · COD10KMAE: 0.054 -> 0.046Improved
add BLIP caption language prompt (ablation)SAM baseline · CAMOS-alpha: 0.790 -> 0.784No clear effect
add vision (BLIP image embedding) prompt (ablation)SAM + Language · CAMOS-alpha: 0.784 -> 0.811Improved
add vision prompt (ablation)SAM + Language · COD10KE-measure: 0.833 -> 0.818Mixed
add dense embedding from SAM image embedding (ablation)SAM + Language + Vision · CAMOweighted F-measure: 0.676 -> 0.712Improved
add dense embedding from SAM image embedding (ablation)SAM + Language + Vision · COD10KMAE: 0.042 -> 0.034Improved
add multi-level adapter (ablation)SAM + Language + Vision + Dense · CHAMELEONS-alpha: 0.872 -> 0.923Improved
add multi-level adapter (ablation)SAM + Language + Vision + Dense · COD10Kweighted F-measure: 0.706 -> 0.808Improved
add multi-level adapter (ablation)SAM + Language + Vision + Dense · CAMOMAE: 0.075 -> 0.059Improved
use MM-SAM instead of SAM-AdapterSAM-Adapter · COD10KS-alpha: 0.883 -> 0.896Improved
use MM-SAM instead of SAM-AdapterSAM-Adapter · CHAMELEONS-alpha: 0.896 -> 0.923Improved

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