{"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/learning-bag-of-features-pooling-for-deep","title":"Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks","arxiv_id":"1707.08105","date":"2017-07-25","proceeding":"ICCV 2017 10","authors":["Nikolaos Passalis","Anastasios Tefas"],"abstract":"Convolutional Neural Networks (CNNs) are well established models capable of\nachieving state-of-the-art classification accuracy for various computer vision\ntasks. However, they are becoming increasingly larger, using millions of\nparameters, while they are restricted to handling images of fixed size. In this\npaper, a quantization-based approach, inspired from the well-known\nBag-of-Features model, is proposed to overcome these limitations. The proposed\napproach, called Convolutional BoF (CBoF), uses RBF neurons to quantize the\ninformation extracted from the convolutional layers and it is able to natively\nclassify images of various sizes as well as to significantly reduce the number\nof parameters in the network. In contrast to other global pooling operators and\nCNN compression techniques the proposed method utilizes a trainable pooling\nlayer that it is end-to-end differentiable, allowing the network to be trained\nusing regular back-propagation and to achieve greater distribution shift\ninvariance than competitive methods. The ability of the proposed method to\nreduce the parameters of the network and increase the classification accuracy\nover other state-of-the-art techniques is demonstrated using three image\ndatasets.","url_abs":"http://arxiv.org/abs/1707.08105v2","url_pdf":"http://arxiv.org/pdf/1707.08105v2.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":"learning-bag-of-features-pooling-for-deep","repo_url":"https://github.com/passalis/cbof","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-bag-of-features-pooling-for-deep","repo_url":"https://github.com/firasl/BoCF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}