{"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/curriculum-temperature-for-knowledge","title":"Curriculum Temperature for Knowledge Distillation","arxiv_id":"2211.16231","date":"2022-11-29","proceeding":null,"authors":["Zheng Li","Xiang Li","Lingfeng Yang","Borui Zhao","RenJie Song","Lei Luo","Jun Li","Jian Yang"],"abstract":"Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature. Specifically, following an easy-to-hard curriculum, we gradually increase the distillation loss w.r.t. the temperature, leading to increased distillation difficulty in an adversarial manner. As an easy-to-use plug-in technique, CTKD can be seamlessly integrated into existing knowledge distillation frameworks and brings general improvements at a negligible additional computation cost. Extensive experiments on CIFAR-100, ImageNet-2012, and MS-COCO demonstrate the effectiveness of our method. Our code is available at https://github.com/zhengli97/CTKD.","url_abs":"https://arxiv.org/abs/2211.16231v3","url_pdf":"https://arxiv.org/pdf/2211.16231v3.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":"curriculum-temperature-for-knowledge","repo_url":"https://github.com/zhengli97/ctkd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"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=2211.16231","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.16231"}},"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/zhengli97/ctkd","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":5,"ran":2,"unverified":8},"by_repo_kind":{"official":{"samples":15,"ran":7,"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":"b9da06d4f527dd6c","entry":"channel_shuffle","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/ShuffleNetv2_Imagenet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/ShuffleNetv2_Imagenet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b9da06d4f527dd6c"}},{"code_sha256_prefix":"d9def42110729a85","entry":"conv1x1","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/resnetv2.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/resnetv2.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":"d9def42110729a85"}},{"code_sha256_prefix":"160bb14bd76201b4","entry":"conv3x3","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/resnetv2.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/resnetv2.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":"160bb14bd76201b4"}},{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/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":"7765583b9e540679","entry":"conv_1x1_bn","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/mobilenetv2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7765583b9e540679"}},{"code_sha256_prefix":"2f7853ff01cbbc29","entry":"conv_bn","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/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":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f7853ff01cbbc29"}},{"code_sha256_prefix":"421fd14c036bc279","entry":"mobilenetv2_T_w","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/mobilenetv2.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/mobilenetv2.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"421fd14c036bc279"}},{"code_sha256_prefix":"fa5e65eaf182f037","entry":"gap_loss","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/resnet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/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":"fa5e65eaf182f037"}},{"code_sha256_prefix":"9b69431119e6f00b","entry":"get_data_folder","repo":"zhengli97/ctkd","repo_kind":"official","path":"dataset/imagenet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/dataset/imagenet.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":"9b69431119e6f00b"}},{"code_sha256_prefix":"94fb66ad6f5924e1","entry":"get_imagenet_dataloader","repo":"zhengli97/ctkd","repo_kind":"official","path":"dataset/imagenet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/dataset/imagenet.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":"94fb66ad6f5924e1"}},{"code_sha256_prefix":"ad816eb6904c00e3","entry":"get_test_loader","repo":"zhengli97/ctkd","repo_kind":"official","path":"dataset/imagenet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/dataset/imagenet.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":"ad816eb6904c00e3"}},{"code_sha256_prefix":"ee9a05c9ee4702a2","entry":"mobilenet_v2","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/mobilenetv2_imagenet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/mobilenetv2_imagenet.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":"ee9a05c9ee4702a2"}},{"code_sha256_prefix":"978acca4eb9c1fc9","entry":"resnet18","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/resnetv2.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/resnetv2.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":"978acca4eb9c1fc9"}},{"code_sha256_prefix":"916d6b0fde048401","entry":"shufflenet_v2_x0_5","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/ShuffleNetv2_Imagenet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/ShuffleNetv2_Imagenet.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":"916d6b0fde048401"}},{"code_sha256_prefix":"c6134299daf274a3","entry":"shufflenet_v2_x1_0","repo":"zhengli97/ctkd","repo_kind":"official","path":"models/ShuffleNetv2_Imagenet.py","file_url":"https://github.com/zhengli97/ctkd/blob/HEAD/models/ShuffleNetv2_Imagenet.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":"c6134299daf274a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}