{"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/possam-panoptic-open-vocabulary-segment-1","title":"PosSAM: Panoptic Open-vocabulary Segment Anything","arxiv_id":"2403.09620","date":"2024-03-14","proceeding":null,"authors":["Vibashan VS","Shubhankar Borse","Hyojin Park","Debasmit Das","Vishal Patel","Munawar Hayat","Fatih Porikli"],"abstract":"In this paper, we introduce an open-vocabulary panoptic segmentation model that effectively unifies the strengths of the Segment Anything Model (SAM) with the vision-language CLIP model in an end-to-end framework. While SAM excels in generating spatially-aware masks, it's decoder falls short in recognizing object class information and tends to oversegment without additional guidance. Existing approaches address this limitation by using multi-stage techniques and employing separate models to generate class-aware prompts, such as bounding boxes or segmentation masks. Our proposed method, PosSAM is an end-to-end model which leverages SAM's spatially rich features to produce instance-aware masks and harnesses CLIP's semantically discriminative features for effective instance classification. Specifically, we address the limitations of SAM and propose a novel Local Discriminative Pooling (LDP) module leveraging class-agnostic SAM and class-aware CLIP features for unbiased open-vocabulary classification. Furthermore, we introduce a Mask-Aware Selective Ensembling (MASE) algorithm that adaptively enhances the quality of generated masks and boosts the performance of open-vocabulary classification during inference for each image. We conducted extensive experiments to demonstrate our methods strong generalization properties across multiple datasets, achieving state-of-the-art performance with substantial improvements over SOTA open-vocabulary panoptic segmentation methods. In both COCO to ADE20K and ADE20K to COCO settings, PosSAM outperforms the previous state-of-the-art methods by a large margin, 2.4 PQ and 4.6 PQ, respectively. Project Website: https://vibashan.github.io/possam-web/.","url_abs":"https://arxiv.org/abs/2403.09620v1","url_pdf":"https://arxiv.org/pdf/2403.09620v1.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":"possam-panoptic-open-vocabulary-segment-1","repo_url":"https://github.com/Vibashan/PosSAM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"open-vocabulary-panoptic-segmentation","task_name":"Open Vocabulary Panoptic Segmentation"},{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"sam","method_name":"SAM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-panoptic-segmentation-on","task":"Open Vocabulary Panoptic Segmentation","dataset":"ADE20K","model":"PosSAM","rank_in_archive_order":2,"of":10,"metrics":{"PQ":"29.2"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-3","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-847","model":"PosSAM","rank_in_archive_order":8,"of":19,"metrics":{"mIoU":"14.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.09620","atlas_url":"https://app.syntology.ai/?focus=2403.09620","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}