{"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/design-of-kernels-in-convolutional-neural","title":"Design of Kernels in Convolutional Neural Networks for Image Classification","arxiv_id":"1511.09231","date":"2015-11-30","proceeding":null,"authors":["Zhun Sun","Mete Ozay","Takayuki Okatani"],"abstract":"Despite the effectiveness of Convolutional Neural Networks (CNNs) for image\nclassification, our understanding of the relationship between shape of\nconvolution kernels and learned representations is limited. In this work, we\nexplore and employ the relationship between shape of kernels which define\nReceptive Fields (RFs) in CNNs for learning of feature representations and\nimage classification. For this purpose, we first propose a feature\nvisualization method for visualization of pixel-wise classification score maps\nof learned features. Motivated by our experimental results, and observations\nreported in the literature for modeling of visual systems, we propose a novel\ndesign of shape of kernels for learning of representations in CNNs. In the\nexperimental results, we achieved a state-of-the-art classification performance\ncompared to a base CNN model [28] by reducing the number of parameters and\ncomputational time of the model using the ILSVRC-2012 dataset [24]. The\nproposed models also outperform the state-of-the-art models employed on the\nCIFAR-10/100 datasets [12] for image classification. Additionally, we analyzed\nthe robustness of the proposed method to occlusion for classification of\npartially occluded images compared with the state-of-the-art methods. Our\nresults indicate the effectiveness of the proposed approach. The code is\navailable in github.com/minogame/caffe-qhconv.","url_abs":"http://arxiv.org/abs/1511.09231v3","url_pdf":"http://arxiv.org/pdf/1511.09231v3.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":"design-of-kernels-in-convolutional-neural","repo_url":"https://github.com/minogame/caffe-qhconv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"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":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}