{"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/oriented-response-networks","title":"Oriented Response Networks","arxiv_id":"1701.01833","date":"2017-01-07","proceeding":"CVPR 2017 7","authors":["Yanzhao Zhou","Qixiang Ye","Qiang Qiu","Jianbin Jiao"],"abstract":"Deep Convolution Neural Networks (DCNNs) are capable of learning\nunprecedentedly effective image representations. However, their ability in\nhandling significant local and global image rotations remains limited. In this\npaper, we propose Active Rotating Filters (ARFs) that actively rotate during\nconvolution and produce feature maps with location and orientation explicitly\nencoded. An ARF acts as a virtual filter bank containing the filter itself and\nits multiple unmaterialised rotated versions. During back-propagation, an ARF\nis collectively updated using errors from all its rotated versions. DCNNs using\nARFs, referred to as Oriented Response Networks (ORNs), can produce\nwithin-class rotation-invariant deep features while maintaining inter-class\ndiscrimination for classification tasks. The oriented response produced by ORNs\ncan also be used for image and object orientation estimation tasks. Over\nmultiple state-of-the-art DCNN architectures, such as VGG, ResNet, and STN, we\nconsistently observe that replacing regular filters with the proposed ARFs\nleads to significant reduction in the number of network parameters and\nimprovement in classification performance. We report the best results on\nseveral commonly used benchmarks.","url_abs":"http://arxiv.org/abs/1701.01833v2","url_pdf":"http://arxiv.org/pdf/1701.01833v2.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":"oriented-response-networks","repo_url":"https://github.com/ZhouYanzhao/ORN","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dcnn","method_name":"DCNN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"ORN","rank_in_archive_order":94,"of":265,"metrics":{"Percentage correct":"97.02"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"ORN","rank_in_archive_order":83,"of":211,"metrics":{"Percentage correct":"83.85"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1701.01833","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}