AI Paper Atlas

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

Diffusion Models for Open-Vocabulary Segmentation

Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 96 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 background prototypes (ablation)OVDiff (SD features) · PASCAL VOCmIoU: 53.2 -> 64.4Improved
add category pre-filtering (ablation)OVDiff (SD features) · PASCAL VOCmIoU: 54.4 -> 64.4Improved
add CutLER for mask extraction (ablation)OVDiff (SD features) · PASCAL VOCmIoU: 60.4 -> 64.4Improved
add sliding window inference (ablation)OVDiff · PASCAL VOCmIoU: 62.2 -> 64.4Improved
add instance and part prototypes to average prototype (ablation)OVDiff · PASCAL VOCmIoU: 62.5 -> 64.4Improved
ensemble SD, CLIP and DINO features instead of SD alone (ablation)OVDiff · PASCAL VOCmIoU: 64.4 -> 66.4Improved
use CLIP keys instead of CLIP patch tokens (ablation)OVDiff · PASCAL VOCmIoU: 51.4 -> 61.8Improved
add category filter to prior methods TCL and OVSegmentor (ablation)TCL, OVSegmentor · PASCAL VOCmIoU: TCL 51.2 -> 51.8; OVSegmentor 53.8 -> 53.7No clear effect
add CutLER majority voting to prior methods (ablation)TCL, OVSegmentor · PASCAL VOCmIoU: TCL 51.2 -> 43.1; OVSegmentor 53.8 -> 38.7Hurt
replace CutLER with supervised SAM or Grounded SAM (ablation)OVDiff · PASCAL VOCmIoU: 66.3 -> 68.5Improved
use newer Stable Diffusion generator (SD 2.0 vs 1.5) (ablation)OVDiff · PASCAL VOCmIoU: 66.4 -> 67.7Improved
vary number of part prototype clusters K from 8 to 64 (ablation)OVDiff · PASCAL VOCmIoU: 63.8 -> 64.4 (K=32)No clear effect

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