{"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-neural-networks-under-stress","title":"Deep Neural Networks Under Stress","arxiv_id":"1605.03498","date":"2016-05-11","proceeding":null,"authors":["Micael Carvalho","Matthieu Cord","Sandra Avila","Nicolas Thome","Eduardo Valle"],"abstract":"In recent years, deep architectures have been used for transfer learning with\nstate-of-the-art performance in many datasets. The properties of their features\nremain, however, largely unstudied under the transfer perspective. In this\nwork, we present an extensive analysis of the resiliency of feature vectors\nextracted from deep models, with special focus on the trade-off between\nperformance and compression rate. By introducing perturbations to image\ndescriptions extracted from a deep convolutional neural network, we change\ntheir precision and number of dimensions, measuring how it affects the final\nscore. We show that deep features are more robust to these disturbances when\ncompared to classical approaches, achieving a compression rate of 98.4%, while\nlosing only 0.88% of their original score for Pascal VOC 2007.","url_abs":"http://arxiv.org/abs/1605.03498v2","url_pdf":"http://arxiv.org/pdf/1605.03498v2.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-neural-networks-under-stress","repo_url":"https://github.com/MicaelCarvalho/DNNsUnderStress","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}