{"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/distilling-out-of-distribution-robustness-1","title":"Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models","arxiv_id":"2311.01441","date":"2023-11-02","proceeding":"NeurIPS 2023 11","authors":["Andy Zhou","Jindong Wang","Yu-Xiong Wang","Haohan Wang"],"abstract":"We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for better teachers by showing strong gains in out-of-distribution robustness when distilling from pretrained foundation models. Following this finding, we propose Discrete Adversarial Distillation (DAD), which leverages a robust teacher to generate adversarial examples and a VQGAN to discretize them, creating more informative samples than standard data augmentation techniques. We provide a theoretical framework for the use of a robust teacher in the knowledge distillation with data augmentation setting and demonstrate strong gains in out-of-distribution robustness and clean accuracy across different student architectures. Notably, our method adds minor computational overhead compared to similar techniques and can be easily combined with other data augmentations for further improvements.","url_abs":"https://arxiv.org/abs/2311.01441v2","url_pdf":"https://arxiv.org/pdf/2311.01441v2.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":"distilling-out-of-distribution-robustness-1","repo_url":"https://github.com/lapisrocks/DiscreteAdversarialDistillation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"Discrete Adversarial Distillation (ViT-B/224)","rank_in_archive_order":26,"of":39,"metrics":{"Top-1 accuracy %":"31.8 "},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-a","task":"Domain Generalization","dataset":"ImageNet-A","model":"Discrete Adversarial Distillation (ResNet-50)","rank_in_archive_order":33,"of":39,"metrics":{"Top-1 accuracy %":"7.7"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-r","task":"Domain Generalization","dataset":"ImageNet-R","model":"Discrete Adversarial Distillation (ViT-B,224)","rank_in_archive_order":14,"of":39,"metrics":{"Top-1 Error Rate":"34.9"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-imagenet-sketch","task":"Domain Generalization","dataset":"ImageNet-Sketch","model":"Discrete Adversarial Distillation (ViT-B, 224)","rank_in_archive_order":13,"of":20,"metrics":{"Top-1 accuracy":"46.1"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"Discrete Adversarial Distillation (ViT-B, 224)","rank_in_archive_order":595,"of":1060,"metrics":{"Top 1 Accuracy":"81.9%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet-v2","task":"Image Classification","dataset":"ImageNet V2","model":"Discrete Adversarial Distillation (ViT-B, 224)","rank_in_archive_order":22,"of":33,"metrics":{"Top 1 Accuracy":"71.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.01441","atlas_url":"https://app.syntology.ai/?focus=2311.01441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01441"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/lapisrocks/DiscreteAdversarialDistillation","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"84d8f5ac4eda7612","entry":"Attack","repo":"lapisrocks/DiscreteAdversarialDistillation","repo_kind":"official","path":"easyrobust/easyrobust/attacks/robustkdattack.py","file_url":"https://github.com/lapisrocks/DiscreteAdversarialDistillation/blob/HEAD/easyrobust/easyrobust/attacks/robustkdattack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"84d8f5ac4eda7612"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}