{"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/image-generation-from-small-datasets-via","title":"Image Generation From Small Datasets via Batch Statistics Adaptation","arxiv_id":"1904.01774","date":"2019-04-03","proceeding":"ICCV 2019 10","authors":["Atsuhiro Noguchi","Tatsuya Harada"],"abstract":"Thanks to the recent development of deep generative models, it is becoming possible to generate high-quality images with both fidelity and diversity. However, the training of such generative models requires a large dataset. To reduce the amount of data required, we propose a new method for transferring prior knowledge of the pre-trained generator, which is trained with a large dataset, to a small dataset in a different domain. Using such prior knowledge, the model can generate images leveraging some common sense that cannot be acquired from a small dataset. In this work, we propose a novel method focusing on the parameters for batch statistics, scale and shift, of the hidden layers in the generator. By training only these parameters in a supervised manner, we achieved stable training of the generator, and our method can generate higher quality images compared to previous methods without collapsing, even when the dataset is small (~100). Our results show that the diversity of the filters acquired in the pre-trained generator is important for the performance on the target domain. Our method makes it possible to add a new class or domain to a pre-trained generator without disturbing the performance on the original domain.","url_abs":"https://arxiv.org/abs/1904.01774v4","url_pdf":"https://arxiv.org/pdf/1904.01774v4.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":"image-generation-from-small-datasets-via","repo_url":"https://github.com/nogu-atsu/small-dataset-image-generation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"image-generation-from-small-datasets-via","repo_url":"https://github.com/MiaoyunZhao/GANTransferLimitedData","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"image-generation-from-small-datasets-via","repo_url":"https://github.com/apple2373/PyTorch-SmallGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"image-generation-from-small-datasets-via","repo_url":"https://github.com/mevius6/smallgan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-ai-ch-priichyaa","task":"Image Generation","dataset":"‘ไอซ์ ปรีชญา’ ลืมปิดไลฟ์สดตอนอาบน้ำ คลิปถูกคนดีแชร์ออนไลน์","model":"as","rank_in_archive_order":1,"of":1,"metrics":{"0-shot MRR":"1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01774"}},"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/MiaoyunZhao/GANTransferLimitedData","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nogu-atsu/small-dataset-image-generation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/apple2373/PyTorch-SmallGAN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mevius6/smallgan","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"listed":{"samples":3,"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":"b3be36dffe58c81c","entry":"load_part_model","repo":"MiaoyunZhao/GANTransferLimitedData","repo_kind":"listed","path":"Flower_[h]our.py","file_url":"https://github.com/MiaoyunZhao/GANTransferLimitedData/blob/HEAD/Flower_%5Bh%5Dour.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3be36dffe58c81c"}},{"code_sha256_prefix":"66246b3d037551d8","entry":"model_equal_all","repo":"MiaoyunZhao/GANTransferLimitedData","repo_kind":"listed","path":"Flower_[h]our.py","file_url":"https://github.com/MiaoyunZhao/GANTransferLimitedData/blob/HEAD/Flower_%5Bh%5Dour.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66246b3d037551d8"}},{"code_sha256_prefix":"9e7bbefa29f18123","entry":"model_equal_part","repo":"MiaoyunZhao/GANTransferLimitedData","repo_kind":"listed","path":"Flower_[h]our.py","file_url":"https://github.com/MiaoyunZhao/GANTransferLimitedData/blob/HEAD/Flower_%5Bh%5Dour.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e7bbefa29f18123"}},{"code_sha256_prefix":"27f00fb3c1db3c49","entry":"backward","repo":"nogu-atsu/small-dataset-image-generation","repo_kind":"official","path":"gen_models/ada_generator.py","file_url":"https://github.com/nogu-atsu/small-dataset-image-generation/blob/HEAD/gen_models/ada_generator.py","link_basis":"first_harvest_node","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":"27f00fb3c1db3c49"}},{"code_sha256_prefix":"db8507e9776f7d80","entry":"load_dataset","repo":"nogu-atsu/small-dataset-image-generation","repo_kind":"official","path":"source/yaml_utils.py","file_url":"https://github.com/nogu-atsu/small-dataset-image-generation/blob/HEAD/source/yaml_utils.py","link_basis":"first_harvest_node","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":"db8507e9776f7d80"}},{"code_sha256_prefix":"619e0c5cf74a6c9f","entry":"load_model","repo":"nogu-atsu/small-dataset-image-generation","repo_kind":"official","path":"source/yaml_utils.py","file_url":"https://github.com/nogu-atsu/small-dataset-image-generation/blob/HEAD/source/yaml_utils.py","link_basis":"first_harvest_node","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":"619e0c5cf74a6c9f"}},{"code_sha256_prefix":"f5837ba49e24a57d","entry":"load_module","repo":"nogu-atsu/small-dataset-image-generation","repo_kind":"official","path":"source/yaml_utils.py","file_url":"https://github.com/nogu-atsu/small-dataset-image-generation/blob/HEAD/source/yaml_utils.py","link_basis":"first_harvest_node","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":"f5837ba49e24a57d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}