{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sign-spatial-information-incorporated","title":"SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation","arxiv_id":"2108.12517","date":"2021-08-27","proceeding":"ICCV 2021 10","authors":["Jiaxin Cheng","Soumyaroop Nandi","Prem Natarajan","Wael Abd-Almageed"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2108.12517v1","url_pdf":"https://arxiv.org/pdf/2108.12517v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"zero-shot-semantic-segmentation","task_name":"Zero-Shot Semantic Segmentation"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-semantic-segmentation-on-coco-stuff","task":"Zero-Shot Semantic Segmentation","dataset":"COCO-Stuff","model":"SIGN","rank_in_archive_order":15,"of":15,"metrics":{"Inductive Setting hIoU":"20.9","Transductive Setting hIoU":"-"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.12517","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}