{"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-object-discovery-and-co","title":"Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming","arxiv_id":"1707.06397","date":"2017-07-20","proceeding":null,"authors":["Xiu-Shen Wei","Chen-Lin Zhang","Jianxin Wu","Chunhua Shen","Zhi-Hua Zhou"],"abstract":"Reusable model design becomes desirable with the rapid expansion of computer\nvision and machine learning applications. In this paper, we focus on the\nreusability of pre-trained deep convolutional models. Specifically, different\nfrom treating pre-trained models as feature extractors, we reveal more\ntreasures beneath convolutional layers, i.e., the convolutional activations\ncould act as a detector for the common object in the image co-localization\nproblem. We propose a simple yet effective method, termed Deep Descriptor\nTransforming (DDT), for evaluating the correlations of descriptors and then\nobtaining the category-consistent regions, which can accurately locate the\ncommon object in a set of unlabeled images, i.e., unsupervised object\ndiscovery. Empirical studies validate the effectiveness of the proposed DDT\nmethod. On benchmark image co-localization datasets, DDT consistently\noutperforms existing state-of-the-art methods by a large margin. Moreover, DDT\nalso demonstrates good generalization ability for unseen categories and\nrobustness for dealing with noisy data. Beyond those, DDT can be also employed\nfor harvesting web images into valid external data sources for improving\nperformance of both image recognition and object detection.","url_abs":"http://arxiv.org/abs/1707.06397v1","url_pdf":"http://arxiv.org/pdf/1707.06397v1.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":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-discovery","task_name":"Object Discovery"},{"task_slug":"single-object-discovery","task_name":"Single-object discovery"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":null,"task_name":"valid"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/single-object-discovery-on-coco-20k","task":"Single-object discovery","dataset":"COCO_20k","model":"DDT+","rank_in_archive_order":10,"of":10,"metrics":{"CorLoc":"38.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.06397","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}