{"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/beta-rank-a-robust-convolutional-filter","title":"Beta-Rank: A Robust Convolutional Filter Pruning Method For Imbalanced Medical Image Analysis","arxiv_id":"2304.07461","date":"2023-04-15","proceeding":null,"authors":["Morteza Homayounfar","Mohamad Koohi-Moghadam","Reza Rawassizadeh","Varut Vardhanabhuti"],"abstract":"As deep neural networks include a high number of parameters and operations, it can be a challenge to implement these models on devices with limited computational resources. Despite the development of novel pruning methods toward resource-efficient models, it has become evident that these models are not capable of handling \"imbalanced\" and \"limited number of data points\". We proposed a novel filter pruning method by considering the input and output of filters along with the values of the filters that deal with imbalanced datasets better than others. Our pruning method considers the fact that all information about the importance of a filter may not be reflected in the value of the filter. Instead, it is reflected in the changes made to the data after the filter is applied to it. In this work, three methods are compared with the same training conditions except for the ranking values of each method, and 14 methods are compared from other papers. We demonstrated that our model performed significantly better than other methods for imbalanced medical datasets. For example, when we removed up to 58% of FLOPs for the IDRID dataset and up to 45% for the ISIC dataset, our model was able to yield an equivalent (or even superior) result to the baseline model. To evaluate FLOP and parameter reduction using our model in real-world settings, we built a smartphone app, where we demonstrated a reduction of up to 79% in memory usage and 72% in prediction time. All codes and parameters for training different models are available at https://github.com/mohofar/Beta-Rank","url_abs":"https://arxiv.org/abs/2304.07461v2","url_pdf":"https://arxiv.org/pdf/2304.07461v2.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":"beta-rank-a-robust-convolutional-filter","repo_url":"https://github.com/mohofar/beta-rank","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"task_slug":"medical-image-classification","task_name":"Medical Image Classification"},{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Beta-Rank","rank_in_archive_order":166,"of":265,"metrics":{"Percentage correct":"93.97"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"Beta-Rank","rank_in_archive_order":158,"of":211,"metrics":{"Accuracy":"74.01","Percentage correct":"74.01"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-classification-on-idrid","task":"Medical Image Classification","dataset":"IDRiD","model":"Beta-Rank","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy":"81.88"},"uses_additional_data":false},{"leaderboard":"/sota/medical-image-classification-on-isic-2017","task":"Medical Image Classification","dataset":"ISIC 2017","model":"Beta-Rank","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"72.44"},"uses_additional_data":false},{"leaderboard":"/sota/network-pruning-on-cifar-100","task":"Network Pruning","dataset":"CIFAR-100","model":"Beta-Rank","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"74.01"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}