{"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/one-shot-transfer-of-affordance-regions","title":"One-Shot Transfer of Affordance Regions? AffCorrs!","arxiv_id":"2209.07147","date":"2022-09-15","proceeding":null,"authors":["Denis Hadjivelichkov","Sicelukwanda Zwane","Marc Peter Deisenroth","Lourdes Agapito","Dimitrios Kanoulas"],"abstract":"In this work, we tackle one-shot visual search of object parts. Given a single reference image of an object with annotated affordance regions, we segment semantically corresponding parts within a target scene. We propose AffCorrs, an unsupervised model that combines the properties of pre-trained DINO-ViT's image descriptors and cyclic correspondences. We use AffCorrs to find corresponding affordances both for intra- and inter-class one-shot part segmentation. This task is more difficult than supervised alternatives, but enables future work such as learning affordances via imitation and assisted teleoperation.","url_abs":"https://arxiv.org/abs/2209.07147v2","url_pdf":"https://arxiv.org/pdf/2209.07147v2.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":"one-shot-transfer-of-affordance-regions","repo_url":"https://github.com/RPL-CS-UCL/UCL-AffCorrs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"one-shot-instance-segmentation","task_name":"One-Shot Instance Segmentation"},{"task_slug":"one-shot-part-segmentation-of-contain","task_name":"One-Shot Part Segmentation of Contain Affordance - Inter Class"},{"task_slug":"one-shot-part-segmentation-of-contain-1","task_name":"One-Shot Part Segmentation of Contain Affordance - Intra Class"},{"task_slug":"one-shot-part-segmentation-of-cut-affordance","task_name":"One-Shot Part Segmentation of Cut Affordance - Inter Class"},{"task_slug":"one-shot-part-segmentation-of-cut-affordance-1","task_name":"One-Shot Part Segmentation of Cut Affordance - Intra Class"},{"task_slug":"one-shot-part-segmentation-of-grasp","task_name":"One-Shot Part Segmentation of Grasp Affordance - Inter Class"},{"task_slug":"one-shot-part-segmentation-of-grasp-1","task_name":"One-Shot Part Segmentation of Grasp Affordance - Intra Class"},{"task_slug":"one-shot-part-segmentation-of-pound","task_name":"One-Shot Part Segmentation of Pound Affordance - Inter Class"},{"task_slug":"one-shot-part-segmentation-of-pound-1","task_name":"One-Shot Part Segmentation of Pound Affordance - Intra Class"},{"task_slug":"one-shot-part-segmentation-of-scoop","task_name":"One-Shot Part Segmentation of Scoop Affordance - Inter Class"},{"task_slug":"one-shot-part-segmentation-of-scoop-1","task_name":"One-Shot Part Segmentation of Scoop Affordance - Intra Class"},{"task_slug":"one-shot-part-segmentation-of-support","task_name":"One-Shot Part Segmentation of Support Affordance - Inter Class"},{"task_slug":"one-shot-part-segmentation-of-support-1","task_name":"One-Shot Part Segmentation of Support Affordance - Intra Class"},{"task_slug":"one-shot-part-segmentation-of-wrap-grasp","task_name":"One-Shot Part Segmentation of Wrap-Grasp Affordance - Inter Class"},{"task_slug":"one-shot-part-segmentation-of-wrap-grasp-1","task_name":"One-Shot Part Segmentation of Wrap-Grasp Affordance - Intra Class"},{"task_slug":"one-shot-segmentation","task_name":"One-Shot Segmentation"}],"methods":[{"method_slug":"affcorrs","method_name":"AffCorrs"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.07147","atlas_url":"https://app.syntology.ai/?focus=2209.07147","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}