{"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-by-on-the-fly-native","title":"Knowledge Distillation by On-the-Fly Native Ensemble","arxiv_id":"1806.04606","date":"2018-06-12","proceeding":"NeurIPS 2018 12","authors":["Xu Lan","Xiatian Zhu","Shaogang Gong"],"abstract":"Knowledge distillation is effective to train small and generalisable network\nmodels for meeting the low-memory and fast running requirements. Existing\noffline distillation methods rely on a strong pre-trained teacher, which\nenables favourable knowledge discovery and transfer but requires a complex\ntwo-phase training procedure. Online counterparts address this limitation at\nthe price of lacking a highcapacity teacher. In this work, we present an\nOn-the-fly Native Ensemble (ONE) strategy for one-stage online distillation.\nSpecifically, ONE trains only a single multi-branch network while\nsimultaneously establishing a strong teacher on-the- fly to enhance the\nlearning of target network. Extensive evaluations show that ONE improves the\ngeneralisation performance a variety of deep neural networks more significantly\nthan alternative methods on four image classification dataset: CIFAR10,\nCIFAR100, SVHN, and ImageNet, whilst having the computational efficiency\nadvantages.","url_abs":"http://arxiv.org/abs/1806.04606v2","url_pdf":"http://arxiv.org/pdf/1806.04606v2.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-by-on-the-fly-native","repo_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"knowledge-distillation-by-on-the-fly-native","repo_url":"https://github.com/jaychoi12/LG_KD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"knowledge-distillation-by-on-the-fly-native","repo_url":"https://github.com/sungnyun/LG-knowledge-distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.04606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.04606"}},"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/jaychoi12/LG_KD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sungnyun/LG-knowledge-distillation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":2,"unverified":4},"by_repo_kind":{"listed":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"3fb68ed6809a8085","entry":"sigmoid_rampup","repo":"Lan1991Xu/ONE_NeurIPS2018","repo_kind":"listed","path":"utils/ramps.py","file_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018/blob/HEAD/utils/ramps.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3fb68ed6809a8085"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"Lan1991Xu/ONE_NeurIPS2018","repo_kind":"listed","path":"models/cifar/resnet.py","file_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018/blob/HEAD/models/cifar/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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"50afa2863ffd9fde","entry":"plot_overlap","repo":"Lan1991Xu/ONE_NeurIPS2018","repo_kind":"listed","path":"utils/logger.py","file_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018/blob/HEAD/utils/logger.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":"50afa2863ffd9fde"}},{"code_sha256_prefix":"c87e7665fde6cdfc","entry":"colorize","repo":"Lan1991Xu/ONE_NeurIPS2018","repo_kind":"listed","path":"utils/visualize.py","file_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018/blob/HEAD/utils/visualize.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":"c87e7665fde6cdfc"}},{"code_sha256_prefix":"d66f0a3cbb86204c","entry":"gauss","repo":"Lan1991Xu/ONE_NeurIPS2018","repo_kind":"listed","path":"utils/visualize.py","file_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018/blob/HEAD/utils/visualize.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":"d66f0a3cbb86204c"}},{"code_sha256_prefix":"1d6e2edb8832d7b0","entry":"get_mean_and_std","repo":"Lan1991Xu/ONE_NeurIPS2018","repo_kind":"listed","path":"utils/misc.py","file_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018/blob/HEAD/utils/misc.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":"1d6e2edb8832d7b0"}},{"code_sha256_prefix":"1394422d51c4b126","entry":"make_image","repo":"Lan1991Xu/ONE_NeurIPS2018","repo_kind":"listed","path":"utils/visualize.py","file_url":"https://github.com/Lan1991Xu/ONE_NeurIPS2018/blob/HEAD/utils/visualize.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":"1394422d51c4b126"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}