AI Paper Atlas

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

LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation

Xinyu Yan, Meijun Sun, Ge-Peng Ji, Fahad Shahbaz Khan, Salman Khan, Deng-Ping Fan

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 4 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 joint macro/micro training with mode switcher (ablation)LawDIS · DIS-TE4max F-measure: 0.912 -> 0.926Improved
fine-tune VAE decoder (ablation)LawDIS · DIS-TE4max F-measure: 0.919 -> 0.926Improved
add language prompts in training and testing (ablation)LawDIS · DIS-TE4max F-measure: 0.912 -> 0.926Improved
add language prompts at test time to prompt-trained model (ablation)LawDIS · DIS-TE4max F-measure: 0.915 -> 0.926Improved
initialise window refinement from initial mask instead of Gaussian noise (ablation)LawDIS Ours-R · DIS-TE4weighted F-measure: 0.843 -> 0.890Improved
add semi-auto window refinement (micro mode) to Ours-S (ablation)LawDIS · DIS-TE4weighted F-measure: +2.0%Improved
use one-step TCD scheduler instead of DDPM 500 steps (ablation)LawDIS Ours-S · DIS-TE4FPS: 0.006 -> 3.09Improved
use one-step TCD instead of DDIM 50 steps (ablation)LawDIS Ours-S · DIS-TE4weighted F-measure: 0.842 -> 0.856Improved
fine-tune VAE with TCD one-step (ablation)LawDIS Ours-S · DIS-TE4weighted F-measure: 0.856 -> 0.890Improved
apply WR strategy as post-refinement to IS-Net (ablation)IS-Net · DIS-TE4weighted F-measure: +6.4%Improved
apply WR strategy as post-refinement to MVANet (ablation)MVANet · DIS-TE4weighted F-measure: +3.2%Improved
feed local patches to existing DIS modelsBiRefNet · DIS-TE4weighted F-measure: -3.9%Hurt

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