{"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/eagleeye-fast-sub-net-evaluation-for","title":"EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning","arxiv_id":"2007.02491","date":"2020-07-06","proceeding":"ECCV 2020 8","authors":["Bailin Li","Bowen Wu","Jiang Su","Guangrun Wang","Liang Lin"],"abstract":"Finding out the computational redundant part of a trained Deep Neural Network (DNN) is the key question that pruning algorithms target on. Many algorithms try to predict model performance of the pruned sub-nets by introducing various evaluation methods. But they are either inaccurate or very complicated for general application. In this work, we present a pruning method called EagleEye, in which a simple yet efficient evaluation component based on adaptive batch normalization is applied to unveil a strong correlation between different pruned DNN structures and their final settled accuracy. This strong correlation allows us to fast spot the pruned candidates with highest potential accuracy without actually fine-tuning them. This module is also general to plug-in and improve some existing pruning algorithms. EagleEye achieves better pruning performance than all of the studied pruning algorithms in our experiments. Concretely, to prune MobileNet V1 and ResNet-50, EagleEye outperforms all compared methods by up to 3.8%. Even in the more challenging experiments of pruning the compact model of MobileNet V1, EagleEye achieves the highest accuracy of 70.9% with an overall 50% operations (FLOPs) pruned. All accuracy results are Top-1 ImageNet classification accuracy. Source code and models are accessible to open-source community https://github.com/anonymous47823493/EagleEye .","url_abs":"https://arxiv.org/abs/2007.02491v2","url_pdf":"https://arxiv.org/pdf/2007.02491v2.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":"eagleeye-fast-sub-net-evaluation-for","repo_url":"https://github.com/anonymous47823493/EagleEye","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"efficient-neural-network","task_name":"Efficient Neural Network"},{"task_slug":"network-pruning","task_name":"Network Pruning"}],"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":"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":"global-average-pooling","method_name":"Global Average Pooling"},{"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-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/network-pruning-on-imagenet","task":"Network Pruning","dataset":"ImageNet","model":"ResNet50-3G FLOPs","rank_in_archive_order":6,"of":16,"metrics":{"Accuracy":"77.1"},"uses_additional_data":false},{"leaderboard":"/sota/network-pruning-on-imagenet","task":"Network Pruning","dataset":"ImageNet","model":"ResNet50-2G FLOPs","rank_in_archive_order":7,"of":16,"metrics":{"Accuracy":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/network-pruning-on-imagenet","task":"Network Pruning","dataset":"ImageNet","model":"ResNet50-1G FLOPs","rank_in_archive_order":11,"of":16,"metrics":{"Accuracy":"74.2"},"uses_additional_data":false},{"leaderboard":"/sota/network-pruning-on-imagenet","task":"Network Pruning","dataset":"ImageNet","model":"ResNet50-1G FLOPs","rank_in_archive_order":12,"of":16,"metrics":{"Accuracy":"74.2"},"uses_additional_data":false},{"leaderboard":"/sota/network-pruning-on-imagenet","task":"Network Pruning","dataset":"ImageNet","model":"MobileNetV1-50% FLOPs","rank_in_archive_order":15,"of":16,"metrics":{"Accuracy":"70.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.02491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02491"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anonymous47823493/EagleEye","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"d7086511790ecbce","entry":"get_pruning_strategy","repo":"anonymous47823493/EagleEye","repo_kind":"official","path":"search.py","file_url":"https://github.com/anonymous47823493/EagleEye/blob/HEAD/search.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7086511790ecbce"}},{"code_sha256_prefix":"6d74ca4acffb5421","entry":"random_compression_scheduler","repo":"anonymous47823493/EagleEye","repo_kind":"official","path":"search.py","file_url":"https://github.com/anonymous47823493/EagleEye/blob/HEAD/search.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d74ca4acffb5421"}},{"code_sha256_prefix":"06b960cab0d3acdc","entry":"train_epoch","repo":"anonymous47823493/EagleEye","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/anonymous47823493/EagleEye/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06b960cab0d3acdc"}},{"code_sha256_prefix":"5fbab09ef66b82e3","entry":"get_channel_config","repo":"anonymous47823493/EagleEye","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/anonymous47823493/EagleEye/blob/HEAD/finetune.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5fbab09ef66b82e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}