{"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/neural-network-pruning-with-residual","title":"Neural Network Pruning with Residual-Connections and Limited-Data","arxiv_id":"1911.08114","date":"2019-11-19","proceeding":"CVPR 2020 6","authors":["Jian-Hao Luo","Jianxin Wu"],"abstract":"Filter level pruning is an effective method to accelerate the inference speed of deep CNN models. Although numerous pruning algorithms have been proposed, there are still two open issues. The first problem is how to prune residual connections. We propose to prune both channels inside and outside the residual connections via a KL-divergence based criterion. The second issue is pruning with limited data. We observe an interesting phenomenon: directly pruning on a small dataset is usually worse than fine-tuning a small model which is pruned or trained from scratch on the large dataset. Knowledge distillation is an effective approach to compensate for the weakness of limited data. However, the logits of a teacher model may be noisy. In order to avoid the influence of label noise, we propose a label refinement approach to solve this problem. Experiments have demonstrated the effectiveness of our method (CURL, Compression Using Residual-connections and Limited-data). CURL significantly outperforms previous state-of-the-art methods on ImageNet. More importantly, when pruning on small datasets, CURL achieves comparable or much better performance than fine-tuning a pretrained small model.","url_abs":"https://arxiv.org/abs/1911.08114v3","url_pdf":"https://arxiv.org/pdf/1911.08114v3.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":"neural-network-pruning-with-residual","repo_url":"https://github.com/Roll920/CURL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1911.08114","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08114"}},"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/Roll920/CURL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"unverified":3},"by_repo_kind":{"listed":{"samples":7,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"Roll920/CURL","repo_kind":"listed","path":"ImageNet/CURL/1_evaluate_filter_importance/model.py","file_url":"https://github.com/Roll920/CURL/blob/HEAD/ImageNet/CURL/1_evaluate_filter_importance/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"Roll920/CURL","repo_kind":"listed","path":"ImageNet/CURL/1_evaluate_filter_importance/model.py","file_url":"https://github.com/Roll920/CURL/blob/HEAD/ImageNet/CURL/1_evaluate_filter_importance/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"160bb14bd76201b4"}},{"code_sha256_prefix":"a0131fb70c267a9e","entry":"conv_1x1_bn","repo":"Roll920/CURL","repo_kind":"listed","path":"ImageNet/CURL/1_evaluate_filter_importance/mobilenetv2.py","file_url":"https://github.com/Roll920/CURL/blob/HEAD/ImageNet/CURL/1_evaluate_filter_importance/mobilenetv2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0131fb70c267a9e"}},{"code_sha256_prefix":"408e747e0425a594","entry":"conv_3x3_bn","repo":"Roll920/CURL","repo_kind":"listed","path":"ImageNet/CURL/1_evaluate_filter_importance/mobilenetv2.py","file_url":"https://github.com/Roll920/CURL/blob/HEAD/ImageNet/CURL/1_evaluate_filter_importance/mobilenetv2.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"408e747e0425a594"}},{"code_sha256_prefix":"986dfbbd10b2f1c1","entry":"resnet50","repo":"Roll920/CURL","repo_kind":"listed","path":"ImageNet/CURL/1_evaluate_filter_importance/model.py","file_url":"https://github.com/Roll920/CURL/blob/HEAD/ImageNet/CURL/1_evaluate_filter_importance/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"986dfbbd10b2f1c1"}},{"code_sha256_prefix":"92ca9ed581275ec9","entry":"resnet50","repo":"Roll920/CURL","repo_kind":"listed","path":"ImageNet/CURL/1_evaluate_filter_importance/pruned_model.py","file_url":"https://github.com/Roll920/CURL/blob/HEAD/ImageNet/CURL/1_evaluate_filter_importance/pruned_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"92ca9ed581275ec9"}},{"code_sha256_prefix":"9c915d8c81f921b4","entry":"resnet50","repo":"Roll920/CURL","repo_kind":"listed","path":"ImageNet/CURL/2_fine_tuning/pruned_model.py","file_url":"https://github.com/Roll920/CURL/blob/HEAD/ImageNet/CURL/2_fine_tuning/pruned_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c915d8c81f921b4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}