{"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/network-slimming-by-slimmable-networks","title":"AutoSlim: Towards One-Shot Architecture Search for Channel Numbers","arxiv_id":"1903.11728","date":"2019-03-27","proceeding":"ICLR 2020 1","authors":["Jiahui Yu","Thomas Huang"],"abstract":"We study how to set channel numbers in a neural network to achieve better accuracy under constrained resources (e.g., FLOPs, latency, memory footprint or model size). A simple and one-shot solution, named AutoSlim, is presented. Instead of training many network samples and searching with reinforcement learning, we train a single slimmable network to approximate the network accuracy of different channel configurations. We then iteratively evaluate the trained slimmable model and greedily slim the layer with minimal accuracy drop. By this single pass, we can obtain the optimized channel configurations under different resource constraints. We present experiments with MobileNet v1, MobileNet v2, ResNet-50 and RL-searched MNasNet on ImageNet classification. We show significant improvements over their default channel configurations. We also achieve better accuracy than recent channel pruning methods and neural architecture search methods. Notably, by setting optimized channel numbers, our AutoSlim-MobileNet-v2 at 305M FLOPs achieves 74.2% top-1 accuracy, 2.4% better than default MobileNet-v2 (301M FLOPs), and even 0.2% better than RL-searched MNasNet (317M FLOPs). Our AutoSlim-ResNet-50 at 570M FLOPs, without depthwise convolutions, achieves 1.3% better accuracy than MobileNet-v1 (569M FLOPs). Code and models will be available at: https://github.com/JiahuiYu/slimmable_networks","url_abs":"https://arxiv.org/abs/1903.11728v2","url_pdf":"https://arxiv.org/pdf/1903.11728v2.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":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/JiahuiYu/slimmable_networks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/Adlik/model_optimizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/xiusu/ViTAS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/2023-MindSpore-1/ms-code-17/tree/main/AutoSlim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/2023-MindSpore-4/Code8/tree/main/AutoSlim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/2024-MindSpore-1/Code6/tree/main/AutoSlim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/Mind23-2/MindCode-10","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/MindSpore-paper-code-3/code1/tree/main/AutoSlim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/MindSpore-paper-code-3/code6/tree/main/AutoSlim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"network-slimming-by-slimmable-networks","repo_url":"https://github.com/open-mmlab/mmrazor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement 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":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"mnasnet","method_name":"MnasNet"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"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":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.11728","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}