AI Paper Atlas

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

FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation

Jie Qin, Jie Wu, Pengxiang Yan, Ming Li, Ren Yuxi, Xuefeng Xiao, Yitong Wang, Rui Wang, Shilei Wen, Xin Pan, Xingang Wang

CVPR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary semantic segmentation · 89 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
use FreeSeg instead of ZSSegopen-vocabulary semantic segmentation · COCOmIoU unseen: 43.6 -> 49.1Improved
use FreeSeg instead of ZSSegopen-vocabulary semantic segmentation · ADE20KmIoU unseen: 20.3 -> 28.6Improved
use FreeSeg instead of ZSIopen-vocabulary instance segmentation · COCOmAP unseen: 13.6 -> 20.6Improved
use FreeSeg instead of ZSSegopen-vocabulary panoptic segmentation · COCOPQ unseen: 9.7 -> 29.8Improved
add an adaptive class prompt (ablation)FreeSeg · COCO semantic segmentationmIoU unseen: 4.9 -> 38.5Improved
add an adaptive task prompt (ablation)FreeSeg with adaptive class prompt · COCO semantic segmentationmIoU unseen: 38.5 -> 41.3Improved
add semantic context interaction (ablation)FreeSeg with adaptive class and task prompts · COCO semantic segmentationmIoU unseen: 41.3 -> 42.6Improved
add test-time prompt tuning (ablation)FreeSeg with adaptive prompts and context interaction · COCO semantic segmentationmIoU unseen: 42.6 -> 43.3Improved
use unified multi-task training instead of single-task training (ablation)FreeSeg · COCO semantic segmentationmIoU unseen: 42.9 -> 43.3Improved
use adaptive prompts instead of fixed templates (ablation)FreeSeg · COCO semantic segmentationmIoU unseen: 33.7 -> 43.3Improved

Later papers that compared with this method

4 later accepted papers report FreeSeg as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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