AI Paper Atlas

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

Open-World Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

Quande Liu, Youpeng Wen, Jianhua Han, Chunjing Xu, Hang Xu, Xiaodan Liang

ECCV 2022 · 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
add vision-based contrasting (Lvision) (ablation)ViL-Seg · PASCAL VOC (all classes unseen)mIoU: 22.05 -> 33.61Improved
add vision-based contrasting (Lvision) (ablation)ViL-Seg · PASCAL VOC (all classes unseen)pixel accuracy: 50.76 -> 75.97Improved
add vision-based contrasting (Lvision) (ablation)ViL-Seg · PASCAL Context (all classes unseen)mIoU: 13.14 -> 15.89Improved
add vision-based contrasting (Lvision) (ablation)ViL-Seg · COCO Stuff (all classes unseen)mIoU: 13.52 -> 16.41Improved
use online clustering head instead of offline K-means (ablation)ViL-Seg · PASCAL VOC (all classes unseen)mIoU: 30.97 -> 33.61Improved
use online clustering head instead of offline K-means (ablation)ViL-Seg · PASCAL VOC (all classes unseen)pixel accuracy: 69.88 -> 75.97Improved
use online clustering head instead of offline K-means (ablation)ViL-Seg · PASCAL Context (all classes unseen)mIoU: 14.82 -> 15.89Improved
use online clustering head instead of offline K-means (ablation)ViL-Seg · COCO Stuff (all classes unseen)mIoU: 15.81 -> 16.41Improved
use online clustering head instead of offline K-means (ablation)ViL-Seg · inference speedcases per second: 8.5 -> 9.8Improved
use online clustering head instead of offline K-means (ablation)ViL-Seg · parametersparams (M): 86.19M -> 86.27MNo clear effect
vary cluster number C (middle values 20, 25 vs 5, 10, 15 or 30) (ablation)ViL-Seg · PASCAL VOC, Context, COCO StuffmIoUMixed
add self-training on top of ViL-SegViL-Seg · PASCAL VOC (unseen classes)mIoU: 34.42 -> 37.30Improved

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