{"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/multi-task-cnn-model-for-attribute-prediction","title":"Multi-task CNN Model for Attribute Prediction","arxiv_id":"1601.00400","date":"2016-01-04","proceeding":null,"authors":["Abrar H. Abdulnabi","Gang Wang","Jiwen Lu","Kui Jia"],"abstract":"This paper proposes a joint multi-task learning algorithm to better predict\nattributes in images using deep convolutional neural networks (CNN). We\nconsider learning binary semantic attributes through a multi-task CNN model,\nwhere each CNN will predict one binary attribute. The multi-task learning\nallows CNN models to simultaneously share visual knowledge among different\nattribute categories. Each CNN will generate attribute-specific feature\nrepresentations, and then we apply multi-task learning on the features to\npredict their attributes. In our multi-task framework, we propose a method to\ndecompose the overall model's parameters into a latent task matrix and\ncombination matrix. Furthermore, under-sampled classifiers can leverage shared\nstatistics from other classifiers to improve their performance. Natural\ngrouping of attributes is applied such that attributes in the same group are\nencouraged to share more knowledge. Meanwhile, attributes in different groups\nwill generally compete with each other, and consequently share less knowledge.\nWe show the effectiveness of our method on two popular attribute datasets.","url_abs":"http://arxiv.org/abs/1601.00400v1","url_pdf":"http://arxiv.org/pdf/1601.00400v1.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":[],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"clothing-attribute-recognition","task_name":"Clothing Attribute Recognition"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/clothing-attribute-recognition-on-clothing","task":"Clothing Attribute Recognition","dataset":"Clothing Attributes Dataset","model":"MG-CNN","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"92.82"},"uses_additional_data":false},{"leaderboard":"/sota/clothing-attribute-recognition-on-clothing","task":"Clothing Attribute Recognition","dataset":"Clothing Attributes Dataset","model":"S-CNN","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"90.43"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1601.00400","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}