{"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/structured-probabilistic-pruning-for","title":"Structured Probabilistic Pruning for Convolutional Neural Network Acceleration","arxiv_id":"1709.06994","date":"2017-09-20","proceeding":null,"authors":["Huan Wang","Qiming Zhang","Yuehai Wang","Haoji Hu"],"abstract":"In this paper, we propose a novel progressive parameter pruning method for\nConvolutional Neural Network acceleration, named Structured Probabilistic\nPruning (SPP), which effectively prunes weights of convolutional layers in a\nprobabilistic manner. Unlike existing deterministic pruning approaches, where\nunimportant weights are permanently eliminated, SPP introduces a pruning\nprobability for each weight, and pruning is guided by sampling from the pruning\nprobabilities. A mechanism is designed to increase and decrease pruning\nprobabilities based on importance criteria in the training process. Experiments\nshow that, with 4x speedup, SPP can accelerate AlexNet with only 0.3% loss of\ntop-5 accuracy and VGG-16 with 0.8% loss of top-5 accuracy in ImageNet\nclassification. Moreover, SPP can be directly applied to accelerate\nmulti-branch CNN networks, such as ResNet, without specific adaptations. Our 2x\nspeedup ResNet-50 only suffers 0.8% loss of top-5 accuracy on ImageNet. We\nfurther show the effectiveness of SPP on transfer learning tasks.","url_abs":"http://arxiv.org/abs/1709.06994v3","url_pdf":"http://arxiv.org/pdf/1709.06994v3.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":"structured-probabilistic-pruning-for","repo_url":"https://github.com/JackBarber98/pruned-nilm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"structured-probabilistic-pruning-for","repo_url":"https://github.com/JackBarber98/prunedNILM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.06994","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}