{"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/augmentation-aware-self-supervision-for-data-1","title":"Augmentation-Aware Self-Supervision for Data-Efficient GAN Training","arxiv_id":"2205.15677","date":"2022-05-31","proceeding":"NeurIPS 2023 11","authors":["Liang Hou","Qi Cao","Yige Yuan","Songtao Zhao","Chongyang Ma","Siyuan Pan","Pengfei Wan","Zhongyuan Wang","HuaWei Shen","Xueqi Cheng"],"abstract":"Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic $-$ harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs.","url_abs":"https://arxiv.org/abs/2205.15677v5","url_pdf":"https://arxiv.org/pdf/2205.15677v5.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":"augmentation-aware-self-supervision-for-data-1","repo_url":"https://github.com/liang-hou/augself-gan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.15677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.15677"}},"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/liang-hou/augself-gan","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":3,"unverified":12},"by_repo_kind":{"official":{"samples":18,"ran":6,"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":"85eb95cce203dfc7","entry":"D_arch","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/BigGAN.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/BigGAN.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85eb95cce203dfc7"}},{"code_sha256_prefix":"e8c308c9283407d7","entry":"G_arch","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/BigGAN.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/BigGAN.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8c308c9283407d7"}},{"code_sha256_prefix":"52d10a10fb72fb9f","entry":"find_classes","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/datasets.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"52d10a10fb72fb9f"}},{"code_sha256_prefix":"c41836f3e51fa8f1","entry":"gram_schmidt","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/layers.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/layers.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c41836f3e51fa8f1"}},{"code_sha256_prefix":"4e6a8faaf8e44abe","entry":"is_image_file","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/datasets.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e6a8faaf8e44abe"}},{"code_sha256_prefix":"79e61b6269a450e8","entry":"make_dataset","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/datasets.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/datasets.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79e61b6269a450e8"}},{"code_sha256_prefix":"37e1e70fdd71c5ac","entry":"DiffAugment","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/DiffAugment_pytorch.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/DiffAugment_pytorch.py","link_basis":"harvester_set","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":"37e1e70fdd71c5ac"}},{"code_sha256_prefix":"f27d575950b15dab","entry":"accumulate_inception_activations","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/inception_tf.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/inception_tf.py","link_basis":"harvester_set","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":"f27d575950b15dab"}},{"code_sha256_prefix":"c4171e8c1ba5ea65","entry":"add_sample_parser","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/utils.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/utils.py","link_basis":"harvester_set","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":"c4171e8c1ba5ea65"}},{"code_sha256_prefix":"16c22401d84c7ba1","entry":"calculate_inception_score","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/inception_tf.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/inception_tf.py","link_basis":"harvester_set","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":"16c22401d84c7ba1"}},{"code_sha256_prefix":"982a26492dc6b7fb","entry":"loss_dcgan_dis","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/losses.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/losses.py","link_basis":"harvester_set","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":"982a26492dc6b7fb"}},{"code_sha256_prefix":"6c34831223553b6f","entry":"loss_dcgan_gen","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/losses.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/losses.py","link_basis":"harvester_set","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":"6c34831223553b6f"}},{"code_sha256_prefix":"290cd37ab0098d5c","entry":"loss_hinge_dis","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/losses.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/losses.py","link_basis":"harvester_set","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":"290cd37ab0098d5c"}},{"code_sha256_prefix":"28d3a35157f2916d","entry":"power_iteration","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/layers.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/layers.py","link_basis":"harvester_set","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":"28d3a35157f2916d"}},{"code_sha256_prefix":"4015ab1f3ab9b881","entry":"proj","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/layers.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/layers.py","link_basis":"harvester_set","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":"4015ab1f3ab9b881"}},{"code_sha256_prefix":"218f3a8a85aeaa48","entry":"rand_brightness","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/DiffAugment_pytorch.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/DiffAugment_pytorch.py","link_basis":"harvester_set","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":"218f3a8a85aeaa48"}},{"code_sha256_prefix":"55891b212e588333","entry":"rand_saturation","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/DiffAugment_pytorch.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/DiffAugment_pytorch.py","link_basis":"harvester_set","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":"55891b212e588333"}},{"code_sha256_prefix":"e6f2eaa40b13c353","entry":"update_config_roots","repo":"liang-hou/augself-gan","repo_kind":"official","path":"augself-biggan/utils.py","file_url":"https://github.com/liang-hou/augself-gan/blob/HEAD/augself-biggan/utils.py","link_basis":"harvester_set","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":"e6f2eaa40b13c353"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}