Papers › SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot...

SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation

27 Aug 2021ICCV 2021 10arXiv:2108.12517archive 2025-07-28

Jiaxin Cheng, Soumyaroop Nandi, Prem Natarajan, Wael Abd-Almageed

Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction with surrounding context motivates us to incorporate spatial information using positional encoding. We improve standard positional encoding by introducing the concept of Relative Positional Encoding, which integrates spatial information at the feature level and can handle arbitrary image sizes. Furthermore, while self-training is widely used in zero-shot semantic segmentation to generate pseudo-labels, we propose a new knowledge-distillation-inspired self-training strategy, namely Annealed Self-Training, which can automatically assign different importance to pseudo-labels to improve performance. We systematically study the proposed Relative Positional Encoding and Annealed Self-Training in a comprehensive experimental evaluation, and our empirical results confirm the effectiveness of our method on three benchmark datasets.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Knowledge DistillationSegmentationSemantic SegmentationZero-Shot LearningZero-Shot Semantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Zero-Shot Semantic Segmentation COCO-Stuff SIGN Inductive Setting hIoU 20.9 #15 of 15 Archive leaderboard report
Zero-Shot Semantic Segmentation COCO-Stuff SIGN Transductive Setting hIoU - #15 of 15 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