{"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/on-the-diversity-and-realism-of-distilled","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","arxiv_id":"2312.03526","date":"2023-12-06","proceeding":"CVPR 2024 1","authors":["Peng Sun","Bei Shi","Daiwei Yu","Tao Lin"],"abstract":"Contemporary machine learning requires training large neural networks on massive datasets and thus faces the challenges of high computational demands. Dataset distillation, as a recent emerging strategy, aims to compress real-world datasets for efficient training. However, this line of research currently struggle with large-scale and high-resolution datasets, hindering its practicality and feasibility. To this end, we re-examine the existing dataset distillation methods and identify three properties required for large-scale real-world applications, namely, realism, diversity, and efficiency. As a remedy, we propose RDED, a novel computationally-efficient yet effective data distillation paradigm, to enable both diversity and realism of the distilled data. Extensive empirical results over various neural architectures and datasets demonstrate the advancement of RDED: we can distill the full ImageNet-1K to a small dataset comprising 10 images per class within 7 minutes, achieving a notable 42% top-1 accuracy with ResNet-18 on a single RTX-4090 GPU (while the SOTA only achieves 21% but requires 6 hours).","url_abs":"https://arxiv.org/abs/2312.03526v2","url_pdf":"https://arxiv.org/pdf/2312.03526v2.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":"on-the-diversity-and-realism-of-distilled","repo_url":"https://github.com/lins-lab/rded","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"on-the-diversity-and-realism-of-distilled","repo_url":"https://github.com/Guang000/Awesome-Dataset-Distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"on-the-diversity-and-realism-of-distilled","repo_url":"https://github.com/he-y/soft-label-pruning-for-dataset-distillation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"on-the-diversity-and-realism-of-distilled","repo_url":"https://github.com/shaoshitong/EDC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"dataset-distillation","task_name":"Dataset Distillation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.03526","atlas_url":"https://app.syntology.ai/?focus=2312.03526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03526"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/shaoshitong/EDC","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/he-y/soft-label-pruning-for-dataset-distillation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Guang000/Awesome-Dataset-Distillation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lins-lab/rded","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":2,"unverified":7},"by_repo_kind":{"official":{"samples":6,"ran":1,"repositories":1},"listed":{"samples":3,"ran":2,"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":"eab4f74c38cc3c8f","entry":"accuracy","repo":"lins-lab/rded","repo_kind":"official","path":"validation/utils.py","file_url":"https://github.com/lins-lab/rded/blob/HEAD/validation/utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eab4f74c38cc3c8f"}},{"code_sha256_prefix":"c0e0d0685f8dc4c7","entry":"gkern","repo":"shaoshitong/EDC","repo_kind":"listed","path":"Branch_ImageNet_10/recover/recover.py","file_url":"https://github.com/shaoshitong/EDC/blob/HEAD/Branch_ImageNet_10/recover/recover.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c0e0d0685f8dc4c7"}},{"code_sha256_prefix":"871f8dea8a811189","entry":"shift_list","repo":"shaoshitong/EDC","repo_kind":"listed","path":"Branch_ImageNet_10/recover/recover.py","file_url":"https://github.com/shaoshitong/EDC/blob/HEAD/Branch_ImageNet_10/recover/recover.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"871f8dea8a811189"}},{"code_sha256_prefix":"b615cefacfc04d10","entry":"batched_forward","repo":"lins-lab/rded","repo_kind":"official","path":"synthesize/utils.py","file_url":"https://github.com/lins-lab/rded/blob/HEAD/synthesize/utils.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":"b615cefacfc04d10"}},{"code_sha256_prefix":"cf303e03d7c1efe6","entry":"epoch","repo":"shaoshitong/EDC","repo_kind":"listed","path":"Branch_CIFAR_10/recover/baseline.py","file_url":"https://github.com/shaoshitong/EDC/blob/HEAD/Branch_CIFAR_10/recover/baseline.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":"cf303e03d7c1efe6"}},{"code_sha256_prefix":"9a700a3b149f4952","entry":"get_parameters","repo":"lins-lab/rded","repo_kind":"official","path":"validation/utils.py","file_url":"https://github.com/lins-lab/rded/blob/HEAD/validation/utils.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":"9a700a3b149f4952"}},{"code_sha256_prefix":"b76a08bec5e010fd","entry":"get_state_dict","repo":"lins-lab/rded","repo_kind":"official","path":"synthesize/utils.py","file_url":"https://github.com/lins-lab/rded/blob/HEAD/synthesize/utils.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":"b76a08bec5e010fd"}},{"code_sha256_prefix":"c209acc6c3e5877a","entry":"keep_top_k","repo":"lins-lab/rded","repo_kind":"official","path":"validation/utils.py","file_url":"https://github.com/lins-lab/rded/blob/HEAD/validation/utils.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":"c209acc6c3e5877a"}},{"code_sha256_prefix":"680f3862844d8a00","entry":"pad","repo":"lins-lab/rded","repo_kind":"official","path":"synthesize/utils.py","file_url":"https://github.com/lins-lab/rded/blob/HEAD/synthesize/utils.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":"680f3862844d8a00"}},{"code_sha256_prefix":"230fb2e9963063c9","entry":"validate","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"230fb2e9963063c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}