{"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/on-advantages-of-mask-level-recognition-for","title":"On Advantages of Mask-level Recognition for Outlier-aware Segmentation","arxiv_id":"2301.03407","date":"2023-01-09","proceeding":null,"authors":["Matej Grcić","Josip Šarić","Siniša Šegvić"],"abstract":"Most dense recognition approaches bring a separate decision in each particular pixel. These approaches deliver competitive performance in usual closed-set setups. However, important applications in the wild typically require strong performance in presence of outliers. We show that this demanding setup greatly benefit from mask-level predictions, even in the case of non-finetuned baseline models. Moreover, we propose an alternative formulation of dense recognition uncertainty that effectively reduces false positive responses at semantic borders. The proposed formulation produces a further improvement over a very strong baseline and sets the new state of the art in outlier-aware semantic segmentation with and without training on negative data. Our contributions also lead to performance improvement in a recent panoptic setup. In-depth experiments confirm that our approach succeeds due to implicit aggregation of pixel-level cues into mask-level predictions.","url_abs":"https://arxiv.org/abs/2301.03407v2","url_pdf":"https://arxiv.org/pdf/2301.03407v2.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":[{"paper_slug":"on-advantages-of-mask-level-recognition-for","repo_url":"https://github.com/matejgrcic/Open-set-M2F","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.03407","atlas_url":"https://app.syntology.ai/?focus=2301.03407","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}