AI Paper Atlas

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

The Power of Prior: Training-Free Open-Vocabulary Semantic Segmentation with LLaVA

Bingfeng Zhang, Siyue Yu, Hui Li, Jiahua Lin, Wenwu Wang, Jimin Xiao

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation

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 query 'Does the image have the class of {}?' vs 'Does the image contain a {}?' (ablation)FSeg-LLaVA1.6 · VOC21mIoU: 62.4 -> 65.9Improved
use visual responses from LLM layers 7-13 instead of 15-22 (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 49.1 -> 68.0Improved
use layers 7-13 instead of deep layers 22-30 (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 15.2 -> 68.0Improved
use layers 7-13 instead of 7-17 (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 66.8 -> 68.0Improved
use both point and box prompts for SAM instead of points only (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 61.4 -> 68.0Improved
use point prompts instead of box prompts (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 57.8 -> 61.4Improved
filter distance map D with attention map MA (Df = D·MA) instead of D alone (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 67.3 -> 68.0Improved
use attention map alone instead of D·MA (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 68.0 -> 27.3Hurt
multiply prototype mask Mv with guidance map Mf instead of Mf alone (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 67.3 -> 68.0Improved
add prototype mask Mv to refinement instead of Mv alone (ablation)FSeg-LLaVA1.5 · VOC21mIoU: 48.4 -> 68.0Improved
scale LLM from Vicuna-7B to Vicuna-13B in LLaVA-1.6FSeg-LLaVA1.6 · VOC21mIoU: 65.9 -> 64.1Hurt
upgrade from LLaVA-1.5 to LLaVA-1.6 (Vicuna-7B)FSeg-LLaVA · Average over 5 benchmarksmIoU: 35.7 -> 36.8Mixed

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