AI Paper Atlas

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

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation

Yasser Benigmim, Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Raoul de Charette

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic 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 FLOSS class-expert fusionCLIP-DINOiser · CityscapesmIoU: 31.3 -> 34.6Improved
add FLOSS class-expert fusionMaskCLIP · VOC20mIoU: 61.8 -> 61.8No clear effect
add FLOSS class-expert fusionNACLIP · ADE20KmIoU: 17.4 -> 18.4Improved
add FLOSS with experts identified on Cityscapes, evaluated on ACDC/BDD/MapillaryCLIP-DINOiser · out-of-domain driving datasets (average)mIoU: 26.4 -> 28.9Improved
add FLOSS with experts identified on CityscapesNACLIP · ACDC FogmIoU: 32.9 -> 32.5Hurt
identify experts from a single Cityscapes imageCLIP-DINOiser + FLOSS · out-of-domain driving datasets (average)mIoU: 26.4 -> 28.3Improved
transfer experts identified on COCO-Stuff to other datasetsCLIP-DINOiser + FLOSS · Cityscapes (all classes)mIoU: 31.1 -> 32.2Improved
fuse by highest-confidence expert instead of averaging all soft maps (ablation)CLIP-DINOiser + FLOSS · CityscapesmIoU: 31.2 -> 34.6Improved
fuse by highest-confidence expert instead of falling back to averaged classifier on conflict (ablation)CLIP-DINOiser + FLOSS · CityscapesmIoU: 32.0 -> 34.6Improved
fuse by highest-confidence expert instead of averaging conflicting experts (ablation)CLIP-DINOiser + FLOSS · CityscapesmIoU: 34.4 -> 34.6Improved
use entropy instead of other unsupervised metrics to pick experts (ablation)CLIP-DINOiser + FLOSS · CityscapesmIoUImproved
use estimated experts instead of true-expert oracle at rho=100% (ablation)CLIP-DINOiser + FLOSS · CityscapesmIoU: 34.1 -> 34.6Improved

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