{"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/deep-relative-attributes","title":"Deep Relative Attributes","arxiv_id":"1512.04103","date":"2015-12-13","proceeding":null,"authors":["Yaser Souri","Erfan Noury","Ehsan Adeli"],"abstract":"Visual attributes are great means of describing images or scenes, in a way\nboth humans and computers understand. In order to establish a correspondence\nbetween images and to be able to compare the strength of each property between\nimages, relative attributes were introduced. However, since their introduction,\nhand-crafted and engineered features were used to learn increasingly complex\nmodels for the problem of relative attributes. This limits the applicability of\nthose methods for more realistic cases. We introduce a deep neural network\narchitecture for the task of relative attribute prediction. A convolutional\nneural network (ConvNet) is adopted to learn the features by including an\nadditional layer (ranking layer) that learns to rank the images based on these\nfeatures. We adopt an appropriate ranking loss to train the whole network in an\nend-to-end fashion. Our proposed method outperforms the baseline and\nstate-of-the-art methods in relative attribute prediction on various coarse and\nfine-grained datasets. Our qualitative results along with the visualization of\nthe saliency maps show that the network is able to learn effective features for\neach specific attribute. Source code of the proposed method is available at\nhttps://github.com/yassersouri/ghiaseddin.","url_abs":"http://arxiv.org/abs/1512.04103v2","url_pdf":"http://arxiv.org/pdf/1512.04103v2.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":"deep-relative-attributes","repo_url":"https://github.com/yassersouri/ghiaseddin","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1512.04103","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}