{"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/effective-semantic-segmentation-in-cataract","title":"Effective semantic segmentation in Cataract Surgery: What matters most?","arxiv_id":"2108.06119","date":"2021-08-13","proceeding":null,"authors":["Theodoros Pissas","Claudio Ravasio","Lyndon Da Cruz","Christos Bergeles"],"abstract":"Our work proposes neural network design choices that set the state-of-the-art on a challenging public benchmark on cataract surgery, CaDIS. Our methodology achieves strong performance across three semantic segmentation tasks with increasingly granular surgical tool class sets by effectively handling class imbalance, an inherent challenge in any surgical video. We consider and evaluate two conceptually simple data oversampling methods as well as different loss functions. We show significant performance gains across network architectures and tasks especially on the rarest tool classes, thereby presenting an approach for achieving high performance when imbalanced granular datasets are considered. Our code and trained models are available at https://github.com/RViMLab/MICCAI2021_Cataract_semantic_segmentation and qualitative results on unseen surgical video can be found at https://youtu.be/twVIPUj1WZM.","url_abs":"https://arxiv.org/abs/2108.06119v1","url_pdf":"https://arxiv.org/pdf/2108.06119v1.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":"effective-semantic-segmentation-in-cataract","repo_url":"https://github.com/rvimlab/miccai2021_cataract_semantic_segmentation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2d-semantic-segmentation-task-1-8-classes","task_name":"2D Semantic Segmentation task 1 (8 classes)"},{"task_slug":"2d-semantic-segmentation-task-2-17-classes","task_name":"2D Semantic Segmentation task 2 (17 classes)"},{"task_slug":"2d-semantic-segmentation-task-3-25-classes","task_name":"2D Semantic Segmentation task 3 (25 classes)"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-semantic-segmentation-task-3-25-classes-on","task":"2D Semantic Segmentation task 3 (25 classes)","dataset":"CaDIS","model":"OCR-R50-Repeat Factor-Lovasz","rank_in_archive_order":1,"of":6,"metrics":{"Mean IoU (test)":"71.94","Mean IoU (val)":"79.4"},"uses_additional_data":false},{"leaderboard":"/sota/2d-semantic-segmentation-task-3-25-classes-on","task":"2D Semantic Segmentation task 3 (25 classes)","dataset":"CaDIS","model":"DeepLabv3+-R50-Repeat Factor-Lovasz","rank_in_archive_order":2,"of":6,"metrics":{"Mean IoU (test)":"70.51","Mean IoU (val)":"77.44"},"uses_additional_data":false},{"leaderboard":"/sota/2d-semantic-segmentation-task-3-25-classes-on","task":"2D Semantic Segmentation task 3 (25 classes)","dataset":"CaDIS","model":"UPN-R50-Repeat Factor-Lovasz","rank_in_archive_order":3,"of":6,"metrics":{"Mean IoU (test)":"70.44","Mean IoU (val)":"75.75"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.06119","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}