{"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/deepconsensus-using-the-consensus-of-features","title":"DeepConsensus: using the consensus of features from multiple layers to attain robust image classification","arxiv_id":"1811.07266","date":"2018-11-18","proceeding":null,"authors":["Yuchen Li","Safwan Hossain","Kiarash Jamali","Frank Rudzicz"],"abstract":"We consider a classifier whose test set is exposed to various perturbations\nthat are not present in the training set. These test samples still contain\nenough features to map them to the same class as their unperturbed counterpart.\nCurrent architectures exhibit rapid degradation of accuracy when trained on\nstandard datasets but then used to classify perturbed samples of that data. To\naddress this, we present a novel architecture named DeepConsensus that\nsignificantly improves generalization to these test-time perturbations. Our key\ninsight is that deep neural networks should directly consider summaries of low\nand high level features when making classifications. Existing convolutional\nneural networks can be augmented with DeepConsensus, leading to improved\nresistance against large and small perturbations on MNIST, EMNIST,\nFashionMNIST, CIFAR10 and SVHN datasets.","url_abs":"http://arxiv.org/abs/1811.07266v3","url_pdf":"http://arxiv.org/pdf/1811.07266v3.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":"deepconsensus-using-the-consensus-of-features","repo_url":"https://github.com/ychnlgy/DeepConsensus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deepconsensus-using-the-consensus-of-features","repo_url":"https://github.com/ychnlgy/DeepConsensus-experimental-FROZEN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}