{"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/wavelet-convolutional-neural-networks-for","title":"Wavelet Convolutional Neural Networks for Texture Classification","arxiv_id":"1707.07394","date":"2017-07-24","proceeding":null,"authors":["Shin Fujieda","Kohei Takayama","Toshiya Hachisuka"],"abstract":"Texture classification is an important and challenging problem in many image\nprocessing applications. While convolutional neural networks (CNNs) achieved\nsignificant successes for image classification, texture classification remains\na difficult problem since textures usually do not contain enough information\nregarding the shape of object. In image processing, texture classification has\nbeen traditionally studied well with spectral analyses which exploit repeated\nstructures in many textures. Since CNNs process images as-is in the spatial\ndomain whereas spectral analyses process images in the frequency domain, these\nmodels have different characteristics in terms of performance. We propose a\nnovel CNN architecture, wavelet CNNs, which integrates a spectral analysis into\nCNNs. Our insight is that the pooling layer and the convolution layer can be\nviewed as a limited form of a spectral analysis. Based on this insight, we\ngeneralize both layers to perform a spectral analysis with wavelet transform.\nWavelet CNNs allow us to utilize spectral information which is lost in\nconventional CNNs but useful in texture classification. The experiments\ndemonstrate that our model achieves better accuracy in texture classification\nthan existing models. We also show that our model has significantly fewer\nparameters than CNNs, making our model easier to train with less memory.","url_abs":"http://arxiv.org/abs/1707.07394v1","url_pdf":"http://arxiv.org/pdf/1707.07394v1.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":"wavelet-convolutional-neural-networks-for","repo_url":"https://github.com/shinfj/WaveletCNN_for_TextureClassification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"unanswered"}},{"paper_slug":"wavelet-convolutional-neural-networks-for","repo_url":"https://github.com/menon92/WaveletCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"texture-classification","task_name":"Texture Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.07394","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}