{"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/unsupervised-multi-object-segmentation-using","title":"Unsupervised Multi-object Segmentation Using Attention and Soft-argmax","arxiv_id":"2205.13271","date":"2022-05-26","proceeding":null,"authors":["Bruno Sauvalle","Arnaud de La Fortelle"],"abstract":"We introduce a new architecture for unsupervised object-centric representation learning and multi-object detection and segmentation, which uses a translation-equivariant attention mechanism to predict the coordinates of the objects present in the scene and to associate a feature vector to each object. A transformer encoder handles occlusions and redundant detections, and a convolutional autoencoder is in charge of background reconstruction. We show that this architecture significantly outperforms the state of the art on complex synthetic benchmarks.","url_abs":"https://arxiv.org/abs/2205.13271v2","url_pdf":"https://arxiv.org/pdf/2205.13271v2.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":"unsupervised-multi-object-segmentation-using","repo_url":"https://github.com/BrunoSauvalle/AST","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-object-segmentation","task_name":"Unsupervised Object Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-object-segmentation-on-clevrtex","task":"Unsupervised Object Segmentation","dataset":"ClevrTex","model":"AST-Seg-B3-CT","rank_in_archive_order":1,"of":12,"metrics":{"MSE":"139±7","mIoU":"79.58±0.54"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-object-segmentation-on-clevrtex","task":"Unsupervised Object Segmentation","dataset":"ClevrTex","model":"AST","rank_in_archive_order":2,"of":12,"metrics":{"MSE":"167± 1","mIoU":"66.62± 0.80"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-object-segmentation-on-1","task":"Unsupervised Object Segmentation","dataset":"ObjectsRoom","model":"AST","rank_in_archive_order":1,"of":5,"metrics":{"ARI-FG":"0.87"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-object-segmentation-on","task":"Unsupervised Object Segmentation","dataset":"ShapeStacks","model":"AST","rank_in_archive_order":1,"of":5,"metrics":{"ARI-FG":"0.82"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.13271","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}