{"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/knowledge-distillation-as-efficient-pre","title":"Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability","arxiv_id":"2203.05180","date":"2022-03-10","proceeding":"CVPR 2022 1","authors":["Ruifei He","Shuyang Sun","Jihan Yang","Song Bai","Xiaojuan Qi"],"abstract":"Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model architecture amount, and the private/inaccessible data, it is not very efficient or possible to pre-train all the model architectures on large-scale datasets. In this work, we investigate an alternative strategy for pre-training, namely Knowledge Distillation as Efficient Pre-training (KDEP), aiming to efficiently transfer the learned feature representation from existing pre-trained models to new student models for future downstream tasks. We observe that existing Knowledge Distillation (KD) methods are unsuitable towards pre-training since they normally distill the logits that are going to be discarded when transferred to downstream tasks. To resolve this problem, we propose a feature-based KD method with non-parametric feature dimension aligning. Notably, our method performs comparably with supervised pre-training counterparts in 3 downstream tasks and 9 downstream datasets requiring 10x less data and 5x less pre-training time. Code is available at https://github.com/CVMI-Lab/KDEP.","url_abs":"https://arxiv.org/abs/2203.05180v2","url_pdf":"https://arxiv.org/pdf/2203.05180v2.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":"knowledge-distillation-as-efficient-pre","repo_url":"https://github.com/cvmi-lab/kdep","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.05180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.05180"}},"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/cvmi-lab/kdep","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/CVMI-Lab/KDEP","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":5,"ran_fixture":1,"unverified":7},"by_repo_kind":{"official":{"samples":13,"ran":6,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/resnet.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/resnet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"a0131fb70c267a9e","entry":"conv_1x1_bn","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/mobilenet.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/mobilenet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a0131fb70c267a9e"}},{"code_sha256_prefix":"408e747e0425a594","entry":"conv_3x3_bn","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/mobilenet.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/mobilenet.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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"408e747e0425a594"}},{"code_sha256_prefix":"d3319e3d34ca90ca","entry":"drop_connect","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/efficientnet_utils.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3319e3d34ca90ca"}},{"code_sha256_prefix":"f15a49337e69e937","entry":"round_filters","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/efficientnet_utils.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f15a49337e69e937"}},{"code_sha256_prefix":"dbc0ca08d119a5a0","entry":"round_repeats","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/efficientnet_utils.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dbc0ca08d119a5a0"}},{"code_sha256_prefix":"1dc5699e5669a244","entry":"RN50","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/clip_prev.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/clip_prev.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1dc5699e5669a244"}},{"code_sha256_prefix":"1d43d3fb2df8185e","entry":"build_model","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/clip_prev.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/clip_prev.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d43d3fb2df8185e"}},{"code_sha256_prefix":"82a7c55ebdb5ddd1","entry":"conv_1x1_bn_pre_relu","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/mobilenet.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/mobilenet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82a7c55ebdb5ddd1"}},{"code_sha256_prefix":"bf71ee950376d6a2","entry":"resnet18","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/resnet.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bf71ee950376d6a2"}},{"code_sha256_prefix":"bcbea8996447cc16","entry":"resnet18_feat","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/resnet.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/resnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bcbea8996447cc16"}},{"code_sha256_prefix":"6df80a5b66c15202","entry":"save_emb","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/entropy.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/entropy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6df80a5b66c15202"}},{"code_sha256_prefix":"e554dee428d119bb","entry":"vis_emb","repo":"CVMI-Lab/KDEP","repo_kind":"official","path":"src/entropy.py","file_url":"https://github.com/CVMI-Lab/KDEP/blob/HEAD/src/entropy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e554dee428d119bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}