{"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/leaving-reality-to-imagination-robust","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","arxiv_id":"2302.02503","date":"2023-02-05","proceeding":null,"authors":["Hritik Bansal","Aditya Grover"],"abstract":"Recent research on robustness has revealed significant performance gaps between neural image classifiers trained on datasets that are similar to the test set, and those that are from a naturally shifted distribution, such as sketches, paintings, and animations of the object categories observed during training. Prior work focuses on reducing this gap by designing engineered augmentations of training data or through unsupervised pretraining of a single large model on massive in-the-wild training datasets scraped from the Internet. However, the notion of a dataset is also undergoing a paradigm shift in recent years. With drastic improvements in the quality, ease-of-use, and access to modern generative models, generated data is pervading the web. In this light, we study the question: How do these generated datasets influence the natural robustness of image classifiers? We find that Imagenet classifiers trained on real data augmented with generated data achieve higher accuracy and effective robustness than standard training and popular augmentation strategies in the presence of natural distribution shifts. We analyze various factors influencing these results, including the choice of conditioning strategies and the amount of generated data. Additionally, we find that the standard ImageNet classifiers suffer a performance degradation of upto 20\\% on the generated data, indicating their fragility at accurately classifying the objects under novel variations. Lastly, we demonstrate that the image classifiers, which have been trained on real data augmented with generated data from the base generative model, exhibit greater resilience to natural distribution shifts compared to the classifiers trained on real data augmented with generated data from the finetuned generative model on the real data. The code, models, and datasets are available at https://github.com/Hritikbansal/generative-robustness.","url_abs":"https://arxiv.org/abs/2302.02503v2","url_pdf":"https://arxiv.org/pdf/2302.02503v2.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":"leaving-reality-to-imagination-robust","repo_url":"https://github.com/hritikbansal/generative-robustness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"robust-classification","task_name":"Robust classification"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.02503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.02503"}},"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/hritikbansal/generative-robustness","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"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":0,"samples":[{"code_sha256_prefix":"36a1160d7f36cda6","entry":"find_classes","repo":"hritikbansal/generative-robustness","repo_kind":"official","path":"generation/DeepAugment/CAE_distort_imagenet.py","file_url":"https://github.com/hritikbansal/generative-robustness/blob/HEAD/generation/DeepAugment/CAE_distort_imagenet.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":"36a1160d7f36cda6"}},{"code_sha256_prefix":"7734eabc3b7c8b24","entry":"train","repo":"hritikbansal/generative-robustness","repo_kind":"official","path":"generation/DeepAugment/train_noise2net.py","file_url":"https://github.com/hritikbansal/generative-robustness/blob/HEAD/generation/DeepAugment/train_noise2net.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":"7734eabc3b7c8b24"}},{"code_sha256_prefix":"33e4a7b9e37d0502","entry":"validate","repo":"hritikbansal/generative-robustness","repo_kind":"official","path":"generation/DeepAugment/train_noise2net.py","file_url":"https://github.com/hritikbansal/generative-robustness/blob/HEAD/generation/DeepAugment/train_noise2net.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":"33e4a7b9e37d0502"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}