{"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/diversity-aware-channel-pruning-for-stylegan","title":"Diversity-aware Channel Pruning for StyleGAN Compression","arxiv_id":"2403.13548","date":"2024-03-20","proceeding":"CVPR 2024 1","authors":["Jiwoo Chung","Sangeek Hyun","Sang-Heon Shim","Jae-Pil Heo"],"abstract":"StyleGAN has shown remarkable performance in unconditional image generation. However, its high computational cost poses a significant challenge for practical applications. Although recent efforts have been made to compress StyleGAN while preserving its performance, existing compressed models still lag behind the original model, particularly in terms of sample diversity. To overcome this, we propose a novel channel pruning method that leverages varying sensitivities of channels to latent vectors, which is a key factor in sample diversity. Specifically, by assessing channel importance based on their sensitivities to latent vector perturbations, our method enhances the diversity of samples in the compressed model. Since our method solely focuses on the channel pruning stage, it has complementary benefits with prior training schemes without additional training cost. Extensive experiments demonstrate that our method significantly enhances sample diversity across various datasets. Moreover, in terms of FID scores, our method not only surpasses state-of-the-art by a large margin but also achieves comparable scores with only half training iterations.","url_abs":"https://arxiv.org/abs/2403.13548v1","url_pdf":"https://arxiv.org/pdf/2403.13548v1.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":"diversity-aware-channel-pruning-for-stylegan","repo_url":"https://github.com/jiwoogit/dcp-gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"unconditional-image-generation","task_name":"Unconditional Image Generation"}],"methods":[{"method_slug":"adaptive-instance-normalization","method_name":"Adaptive Instance Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"},{"method_slug":"stylegan","method_name":"StyleGAN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.13548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13548"}},"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":"deterministic:regex_extraction","url":"https://github.com/jiwoogit/DCP-GAN","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"official":{"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":3,"samples":[{"code_sha256_prefix":"906a65b5c3852c69","entry":"PCAEstimator","repo":"jiwoogit/DCP-GAN","repo_kind":"official","path":"Util/diversity_aware_pruning.py","file_url":"https://github.com/jiwoogit/DCP-GAN/blob/HEAD/Util/diversity_aware_pruning.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"906a65b5c3852c69"}},{"code_sha256_prefix":"a8ff6a12f2a7e01d","entry":"get_estimator","repo":"jiwoogit/DCP-GAN","repo_kind":"official","path":"Util/diversity_aware_pruning.py","file_url":"https://github.com/jiwoogit/DCP-GAN/blob/HEAD/Util/diversity_aware_pruning.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a8ff6a12f2a7e01d"}},{"code_sha256_prefix":"5883250cc2d03cab","entry":"Get_Diversity_Pruning_Score","repo":"jiwoogit/DCP-GAN","repo_kind":"official","path":"Util/diversity_aware_pruning.py","file_url":"https://github.com/jiwoogit/DCP-GAN/blob/HEAD/Util/diversity_aware_pruning.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":"5883250cc2d03cab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}