{"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/using-filter-banks-in-convolutional-neural","title":"Using Filter Banks in Convolutional Neural Networks for Texture Classification","arxiv_id":"1601.02919","date":"2016-01-12","proceeding":null,"authors":["Vincent Andrearczyk","Paul F. Whelan"],"abstract":"Deep learning has established many new state of the art solutions in the last\ndecade in areas such as object, scene and speech recognition. In particular\nConvolutional Neural Network (CNN) is a category of deep learning which obtains\nexcellent results in object detection and recognition tasks. Its architecture\nis indeed well suited to object analysis by learning and classifying complex\n(deep) features that represent parts of an object or the object itself.\nHowever, some of its features are very similar to texture analysis methods. CNN\nlayers can be thought of as filter banks of complexity increasing with the\ndepth. Filter banks are powerful tools to extract texture features and have\nbeen widely used in texture analysis. In this paper we develop a simple network\narchitecture named Texture CNN (T-CNN) which explores this observation. It is\nbuilt on the idea that the overall shape information extracted by the fully\nconnected layers of a classic CNN is of minor importance in texture analysis.\nTherefore, we pool an energy measure from the last convolution layer which we\nconnect to a fully connected layer. We show that our approach can improve the\nperformance of a network while greatly reducing the memory usage and\ncomputation.","url_abs":"http://arxiv.org/abs/1601.02919v5","url_pdf":"http://arxiv.org/pdf/1601.02919v5.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":"using-filter-banks-in-convolutional-neural","repo_url":"https://github.com/v-andrearczyk/caffe-TCNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"using-filter-banks-in-convolutional-neural","repo_url":"https://github.com/Shantanu48114860/MTL-TCNN3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"texture-classification","task_name":"Texture Classification"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1601.02919","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}