Papers › Zero-Shot Semantic Segmentation

Zero-Shot Semantic Segmentation

3 Jun 2019NeurIPS 2019 12arXiv:1906.00817archive 2025-07-28

Maxime Bucher, Tuan-Hung Vu, Matthieu Cord, Patrick Pérez

Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object categories with zero training examples. To this end, we present a novel architecture, ZS3Net, combining a deep visual segmentation model with an approach to generate visual representations from semantic word embeddings. By this way, ZS3Net addresses pixel classification tasks where both seen and unseen categories are faced at test time (so called "generalized" zero-shot classification). Performance is further improved by a self-training step that relies on automatic pseudo-labeling of pixels from unseen classes. On the two standard segmentation datasets, Pascal-VOC and Pascal-Context, we propose zero-shot benchmarks and set competitive baselines. For complex scenes as ones in the Pascal-Context dataset, we extend our approach by using a graph-context encoding to fully leverage spatial context priors coming from class-wise segmentation maps.

Paper PDF Conference PDF Code

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

Code

valeoai/ZS3 officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

bcmi/CaGNetv2-Zero-Shot-Semantic-Segmentation mentioned 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

General Classification Segmentation Semantic Segmentation Word Embeddings Zero-Shot Learning Zero-Shot Semantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Zero-Shot Learning	PASCAL Context	ZS3Net	k=10 mIOU	26.3	#1 of 1	Archive leaderboard	report
Zero-Shot Semantic Segmentation	COCO-Stuff	ZS5	Inductive Setting hIoU	15.0	#12 of 15	Archive leaderboard	report
Zero-Shot Semantic Segmentation	COCO-Stuff	ZS5	Transductive Setting hIoU	16.2	#12 of 15	Archive leaderboard	report
Zero-Shot Semantic Segmentation	PASCAL VOC	ZS5	Transductive Setting hIoU	33.8	#11 of 13	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