{"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/a-systematic-comparison-of-bayesian-deep","title":"A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks","arxiv_id":"1912.10481","date":"2019-12-22","proceeding":null,"authors":["Angelos Filos","Sebastian Farquhar","Aidan N. Gomez","Tim G. J. Rudner","Zachary Kenton","Lewis Smith","Milad Alizadeh","Arnoud de Kroon","Yarin Gal"],"abstract":"Evaluation of Bayesian deep learning (BDL) methods is challenging. We often seek to evaluate the methods' robustness and scalability, assessing whether new tools give `better' uncertainty estimates than old ones. These evaluations are paramount for practitioners when choosing BDL tools on-top of which they build their applications. Current popular evaluations of BDL methods, such as the UCI experiments, are lacking: Methods that excel with these experiments often fail when used in application such as medical or automotive, suggesting a pertinent need for new benchmarks in the field. We propose a new BDL benchmark with a diverse set of tasks, inspired by a real-world medical imaging application on \\emph{diabetic retinopathy diagnosis}. Visual inputs (512x512 RGB images of retinas) are considered, where model uncertainty is used for medical pre-screening---i.e. to refer patients to an expert when model diagnosis is uncertain. Methods are then ranked according to metrics derived from expert-domain to reflect real-world use of model uncertainty in automated diagnosis. We develop multiple tasks that fall under this application, including out-of-distribution detection and robustness to distribution shift. We then perform a systematic comparison of well-tuned BDL techniques on the various tasks. From our comparison we conclude that some current techniques which solve benchmarks such as UCI `overfit' their uncertainty to the dataset---when evaluated on our benchmark these underperform in comparison to simpler baselines. The code for the benchmark, its baselines, and a simple API for evaluating new BDL tools are made available at https://github.com/oatml/bdl-benchmarks.","url_abs":"https://arxiv.org/abs/1912.10481v1","url_pdf":"https://arxiv.org/pdf/1912.10481v1.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":"a-systematic-comparison-of-bayesian-deep","repo_url":"https://github.com/OATML/bdl-benchmarks","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1912.10481","atlas_url":"https://app.syntology.ai/?focus=1912.10481","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.10481"}},"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/OATML/bdl-benchmarks","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":"b860dcbf185f6bd8","entry":"VGGDrop","repo":"OATML/bdl-benchmarks","repo_kind":"official","path":"baselines/diabetic_retinopathy_diagnosis/mc_dropout/model.py","file_url":"https://github.com/OATML/bdl-benchmarks/blob/HEAD/baselines/diabetic_retinopathy_diagnosis/mc_dropout/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b860dcbf185f6bd8"}},{"code_sha256_prefix":"502c7569e93f0e05","entry":"VGGFlipout","repo":"OATML/bdl-benchmarks","repo_kind":"official","path":"baselines/diabetic_retinopathy_diagnosis/mfvi/model.py","file_url":"https://github.com/OATML/bdl-benchmarks/blob/HEAD/baselines/diabetic_retinopathy_diagnosis/mfvi/model.py","link_basis":"first_harvest_node","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":"502c7569e93f0e05"}},{"code_sha256_prefix":"28aaca022159c9f5","entry":"predict","repo":"OATML/bdl-benchmarks","repo_kind":"official","path":"baselines/diabetic_retinopathy_diagnosis/deep_ensembles/model.py","file_url":"https://github.com/OATML/bdl-benchmarks/blob/HEAD/baselines/diabetic_retinopathy_diagnosis/deep_ensembles/model.py","link_basis":"first_harvest_node","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":"28aaca022159c9f5"}},{"code_sha256_prefix":"7f22697a838a0388","entry":"predict","repo":"OATML/bdl-benchmarks","repo_kind":"official","path":"baselines/diabetic_retinopathy_diagnosis/deterministic/model.py","file_url":"https://github.com/OATML/bdl-benchmarks/blob/HEAD/baselines/diabetic_retinopathy_diagnosis/deterministic/model.py","link_basis":"first_harvest_node","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":"7f22697a838a0388"}},{"code_sha256_prefix":"c4bfcb312c170974","entry":"predict","repo":"OATML/bdl-benchmarks","repo_kind":"official","path":"baselines/diabetic_retinopathy_diagnosis/ensemble_mc_dropout/model.py","file_url":"https://github.com/OATML/bdl-benchmarks/blob/HEAD/baselines/diabetic_retinopathy_diagnosis/ensemble_mc_dropout/model.py","link_basis":"first_harvest_node","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":"c4bfcb312c170974"}},{"code_sha256_prefix":"da7fb6e77030b6c7","entry":"predict","repo":"OATML/bdl-benchmarks","repo_kind":"official","path":"baselines/diabetic_retinopathy_diagnosis/mc_dropout/model.py","file_url":"https://github.com/OATML/bdl-benchmarks/blob/HEAD/baselines/diabetic_retinopathy_diagnosis/mc_dropout/model.py","link_basis":"first_harvest_node","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":"da7fb6e77030b6c7"}},{"code_sha256_prefix":"026cbf4b9aa2c622","entry":"predict","repo":"OATML/bdl-benchmarks","repo_kind":"official","path":"baselines/diabetic_retinopathy_diagnosis/mfvi/model.py","file_url":"https://github.com/OATML/bdl-benchmarks/blob/HEAD/baselines/diabetic_retinopathy_diagnosis/mfvi/model.py","link_basis":"first_harvest_node","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":"026cbf4b9aa2c622"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}