{"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/emphasizing-discriminative-features-for","title":"Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios","arxiv_id":"2410.17193","date":"2024-10-22","proceeding":"CVPR 2025 1","authors":["Kai Wang","Zekai Li","Zhi-Qi Cheng","Samir Khaki","Ahmad Sajedi","Ramakrishna Vedantam","Konstantinos N Plataniotis","Alexander Hauptmann","Yang You"],"abstract":"Dataset distillation has demonstrated strong performance on simple datasets like CIFAR, MNIST, and TinyImageNet but struggles to achieve similar results in more complex scenarios. In this paper, we propose EDF (emphasizes the discriminative features), a dataset distillation method that enhances key discriminative regions in synthetic images using Grad-CAM activation maps. Our approach is inspired by a key observation: in simple datasets, high-activation areas typically occupy most of the image, whereas in complex scenarios, the size of these areas is much smaller. Unlike previous methods that treat all pixels equally when synthesizing images, EDF uses Grad-CAM activation maps to enhance high-activation areas. From a supervision perspective, we downplay supervision signals that have lower losses, as they contain common patterns. Additionally, to help the DD community better explore complex scenarios, we build the Complex Dataset Distillation (Comp-DD) benchmark by meticulously selecting sixteen subsets, eight easy and eight hard, from ImageNet-1K. In particular, EDF consistently outperforms SOTA results in complex scenarios, such as ImageNet-1K subsets. Hopefully, more researchers will be inspired and encouraged to improve the practicality and efficacy of DD. Our code and benchmark will be made public at https://github.com/NUS-HPC-AI-Lab/EDF.","url_abs":"https://arxiv.org/abs/2410.17193v2","url_pdf":"https://arxiv.org/pdf/2410.17193v2.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":"emphasizing-discriminative-features-for","repo_url":"https://github.com/nus-hpc-ai-lab/edf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dataset-distillation","task_name":"Dataset Distillation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.17193","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17193"}},"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/nus-hpc-ai-lab/edf","reach":{"status":"ok"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"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":9,"samples":[{"code_sha256_prefix":"2e6f03f47dc4131d","entry":"VGG11","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"networks.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/networks.py","link_basis":"harvester_set","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":"2e6f03f47dc4131d"}},{"code_sha256_prefix":"cce7c5ae5e902d5b","entry":"VGG11BN","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"networks.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/networks.py","link_basis":"harvester_set","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":"cce7c5ae5e902d5b"}},{"code_sha256_prefix":"57fb277537295695","entry":"VGG11_Tiny","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"networks.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/networks.py","link_basis":"harvester_set","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":"57fb277537295695"}},{"code_sha256_prefix":"144990ff9fba8362","entry":"calculate_percentage_above_threshold","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"calculate_the_ratio.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/calculate_the_ratio.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":"144990ff9fba8362"}},{"code_sha256_prefix":"a2a046f8a0efc9e5","entry":"create_simple_tensor_dataset","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"comp-dd/load_data.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/comp-dd/load_data.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":"a2a046f8a0efc9e5"}},{"code_sha256_prefix":"04b461b528d0f0a4","entry":"create_soft_mask","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"distill/edf_distill.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/distill/edf_distill.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":"04b461b528d0f0a4"}},{"code_sha256_prefix":"b69bf62faf779ca5","entry":"load_comp_dd","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"comp-dd/load_data.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/comp-dd/load_data.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":"b69bf62faf779ca5"}},{"code_sha256_prefix":"cb45ca636db0e0ea","entry":"load_percentages","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"calculate_the_ratio.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/calculate_the_ratio.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":"cb45ca636db0e0ea"}},{"code_sha256_prefix":"ad84d1668d85b6ba","entry":"process_file","repo":"nus-hpc-ai-lab/edf","repo_kind":"official","path":"calculate_the_ratio.py","file_url":"https://github.com/nus-hpc-ai-lab/edf/blob/HEAD/calculate_the_ratio.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":"ad84d1668d85b6ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}