Papers › In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation

In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation

9 Aug 2024arXiv:2408.04961archive 2025-07-28

Dahyun Kang, Minsu Cho

We present lazy visual grounding, a two-stage approach of unsupervised object mask discovery followed by object grounding, for open-vocabulary semantic segmentation. Plenty of the previous art casts this task as pixel-to-text classification without object-level comprehension, leveraging the image-to-text classification capability of pretrained vision-and-language models. We argue that visual objects are distinguishable without the prior text information as segmentation is essentially a vision task. Lazy visual grounding first discovers object masks covering an image with iterative Normalized cuts and then later assigns text on the discovered objects in a late interaction manner. Our model requires no additional training yet shows great performance on five public datasets: Pascal VOC, Pascal Context, COCO-object, COCO-stuff, and ADE 20K. Especially, the visually appealing segmentation results demonstrate the model capability to localize objects precisely. Paper homepage: https://cvlab.postech.ac.kr/research/lazygrounding

Paper PDF Code

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

dahyun-kang/lazygrounding officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image to text Object Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation Segmentation Semantic Segmentation Text Classification Visual Grounding text-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Open Vocabulary Semantic Segmentation	ADE20K-150	LaVG	mIoU	15.8	#22 of 23	Archive leaderboard	report
Open Vocabulary Semantic Segmentation	COCO-Stuff-171	LaVG	mIoU	23.2	#5 of 7	Archive leaderboard	report
Open Vocabulary Semantic Segmentation	PASCAL Context-59	LaVG	mIoU	34.7	#21 of 24	Archive leaderboard	report
Open Vocabulary Semantic Segmentation	PascalVOC-20	LaVG	mIoU	82.5	#17 of 20	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections