{"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/object-recognition-with-and-without-objects","title":"Object Recognition with and without Objects","arxiv_id":"1611.06596","date":"2016-11-20","proceeding":null,"authors":["Zhuotun Zhu","Lingxi Xie","Alan L. Yuille"],"abstract":"While recent deep neural networks have achieved a promising performance on\nobject recognition, they rely implicitly on the visual contents of the whole\nimage. In this paper, we train deep neural net- works on the foreground\n(object) and background (context) regions of images respectively. Consider- ing\nhuman recognition in the same situations, net- works trained on the pure\nbackground without ob- jects achieves highly reasonable recognition performance\nthat beats humans by a large margin if only given context. However, humans\nstill outperform networks with pure object available, which indicates networks\nand human beings have different mechanisms in understanding an image.\nFurthermore, we straightforwardly combine multiple trained networks to explore\ndifferent visual cues learned by different networks. Experiments show that\nuseful visual hints can be explicitly learned separately and then combined to\nachieve higher performance, which verifies the advantages of the proposed\nframework.","url_abs":"http://arxiv.org/abs/1611.06596v3","url_pdf":"http://arxiv.org/pdf/1611.06596v3.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":"object-recognition-with-and-without-objects","repo_url":"https://github.com/sunformoon/ObjectRecognitionWithWithoutObjects","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.06596","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}