{"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/using-pre-training-can-improve-model","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","arxiv_id":"1901.09960","date":"2019-01-28","proceeding":null,"authors":["Dan Hendrycks","Kimin Lee","Mantas Mazeika"],"abstract":"He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional classification metrics, it improves model robustness and uncertainty estimates. Through extensive experiments on adversarial examples, label corruption, class imbalance, out-of-distribution detection, and confidence calibration, we demonstrate large gains from pre-training and complementary effects with task-specific methods. We introduce adversarial pre-training and show approximately a 10% absolute improvement over the previous state-of-the-art in adversarial robustness. In some cases, using pre-training without task-specific methods also surpasses the state-of-the-art, highlighting the need for pre-training when evaluating future methods on robustness and uncertainty tasks.","url_abs":"https://arxiv.org/abs/1901.09960v5","url_pdf":"https://arxiv.org/pdf/1901.09960v5.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":"using-pre-training-can-improve-model","repo_url":"https://github.com/hendrycks/pre-training","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"adversarial-robustness","task_name":"Adversarial Robustness"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.09960","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.09960"}},"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/hendrycks/pre-training","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":1,"ran_draft_wrong":3,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"05eda95f9800a1e9","entry":"cosine_annealing","repo":"hendrycks/pre-training","repo_kind":"official","path":"downsampled_train/baseline.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/downsampled_train/baseline.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"05eda95f9800a1e9"}},{"code_sha256_prefix":"b16e920816efe253","entry":"normalize_l2","repo":"hendrycks/pre-training","repo_kind":"official","path":"robustness/adversarial/attacks.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/robustness/adversarial/attacks.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b16e920816efe253"}},{"code_sha256_prefix":"5b640b32a444ae38","entry":"tensor_clamp","repo":"hendrycks/pre-training","repo_kind":"official","path":"robustness/adversarial/attacks.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/robustness/adversarial/attacks.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b640b32a444ae38"}},{"code_sha256_prefix":"63b4423b18c974ad","entry":"tensor_clamp_l2","repo":"hendrycks/pre-training","repo_kind":"official","path":"robustness/adversarial/attacks.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/robustness/adversarial/attacks.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63b4423b18c974ad"}},{"code_sha256_prefix":"74fa122d15c0f3ce","entry":"flip_labels_C","repo":"hendrycks/pre-training","repo_kind":"official","path":"robustness/label_corruption/load_corrupted_ours_hierarchical.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/robustness/label_corruption/load_corrupted_ours_hierarchical.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74fa122d15c0f3ce"}},{"code_sha256_prefix":"72410f1136cc7250","entry":"make_layers","repo":"hendrycks/pre-training","repo_kind":"official","path":"downsampled_train/models/allconv.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/downsampled_train/models/allconv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72410f1136cc7250"}},{"code_sha256_prefix":"ba6749b25e502f54","entry":"uniform_mix_C","repo":"hendrycks/pre-training","repo_kind":"official","path":"robustness/label_corruption/load_corrupted_ours_hierarchical.py","file_url":"https://github.com/hendrycks/pre-training/blob/HEAD/robustness/label_corruption/load_corrupted_ours_hierarchical.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ba6749b25e502f54"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}