{"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/explanation-based-weakly-supervised-learning","title":"Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks","arxiv_id":"2006.09562","date":"2020-06-16","proceeding":"ECCV 2020 8","authors":["Federico Baldassarre","Kevin Smith","Josephine Sullivan","Hossein Azizpour"],"abstract":"Visual relationship detection is fundamental for holistic image understanding. However, localizing and classifying (subject, predicate, object) triplets constitutes a hard learning objective due to the combinatorial explosion of possible relationships, their long-tail distribution in natural images, and an expensive annotation process. This paper introduces a novel weakly-supervised method for visual relationship detection that relies only on image-level predicate annotations. A graph neural network is trained to classify the predicates in an image from the graph representation of all objects, implicitly encoding an inductive bias for pairwise relationships. We then frame relationship detection as the explanation of such a predicate classifier, i.e. we reconstruct a complete relationship by recovering the subject and the object of a predicted predicate. Using this novel technique and minimal labels, we present comparable results to recent fully-supervised and weakly-supervised methods on three diverse and challenging datasets: HICO-DET for human-object interaction, Visual Relationship Detection for generic object-to-object relationships, and UnRel for unusual relationships.","url_abs":"https://arxiv.org/abs/2006.09562v1","url_pdf":"https://arxiv.org/pdf/2006.09562v1.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":"explanation-based-weakly-supervised-learning","repo_url":"https://github.com/baldassarreFe/ws-vrd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"human-object-interaction-detection","task_name":"Human-Object Interaction Detection"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"object","task_name":"Object"},{"task_slug":"relationship-detection","task_name":"Relationship Detection"},{"task_slug":"visual-relationship-detection","task_name":"Visual Relationship Detection"},{"task_slug":"weakly-supervised-learning","task_name":"Weakly-supervised Learning"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.09562","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}