{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/masksembles-for-uncertainty-estimation","title":"Masksembles for Uncertainty Estimation","arxiv_id":"2012.08334","date":"2020-12-15","proceeding":"CVPR 2021 1","authors":["Nikita Durasov","Timur Bagautdinov","Pierre Baque","Pascal Fua"],"abstract":"Deep neural networks have amply demonstrated their prowess but estimating the reliability of their predictions remains challenging. Deep Ensembles are widely considered as being one of the best methods for generating uncertainty estimates but are very expensive to train and evaluate. MC-Dropout is another popular alternative, which is less expensive, but also less reliable. Our central intuition is that there is a continuous spectrum of ensemble-like models of which MC-Dropout and Deep Ensembles are extreme examples. The first uses an effectively infinite number of highly correlated models while the second relies on a finite number of independent models. To combine the benefits of both, we introduce Masksembles. Instead of randomly dropping parts of the network as in MC-dropout, Masksemble relies on a fixed number of binary masks, which are parameterized in a way that allows to change correlations between individual models. Namely, by controlling the overlap between the masks and their density one can choose the optimal configuration for the task at hand. This leads to a simple and easy to implement method with performance on par with Ensembles at a fraction of the cost. We experimentally validate Masksembles on two widely used datasets, CIFAR10 and ImageNet.","url_abs":"https://arxiv.org/abs/2012.08334v2","url_pdf":"https://arxiv.org/pdf/2012.08334v2.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":"masksembles-for-uncertainty-estimation","repo_url":"https://github.com/nikitadurasov/masksembles","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"masksembles-for-uncertainty-estimation","repo_url":"https://github.com/weizheliu/cross-domain-crowd-counting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"masksembles-for-uncertainty-estimation","repo_url":"https://github.com/ensta-u2is/torch-uncertainty","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"masksembles-for-uncertainty-estimation","repo_url":"https://github.com/lightning-uq-box/lightning-uq-box","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classifier-calibration","task_name":"Classifier calibration"},{"task_slug":"ensemble-learning","task_name":"Ensemble Learning"},{"task_slug":"out-of-distribution-detection","task_name":"Out-of-Distribution Detection"},{"task_slug":"robust-classification","task_name":"Robust classification"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[{"method_slug":"deep-ensembles","method_name":"Deep Ensembles"},{"method_slug":"monte-carlo-dropout","method_name":"Monte Carlo Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.08334","atlas_url":"https://app.syntology.ai/?focus=2012.08334","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2012.08334"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2012.08334\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2012.08334"},"call":"get_concepts_for_paper(arxiv_id=\"2012.08334\")"}],"by_repo":[{"repo":"nikitadurasov/masksembles","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"weizheliu/cross-domain-crowd-counting","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ensta-u2is/torch-uncertainty","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2010.06610","2203.09168","2311.01434"],"harvested_for_calls":[{"arxiv_id":"2010.06610","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.06610"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.06610\")"},{"arxiv_id":"2203.09168","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.09168"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.09168\")"},{"arxiv_id":"2311.01434","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2311.01434"},"call":"get_harvested_code_for_paper(arxiv_id=\"2311.01434\")"}]},{"repo":"lightning-uq-box/lightning-uq-box","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["2009.14193","2211.11435","2404.11599"],"harvested_for_calls":[{"arxiv_id":"2009.14193","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2009.14193"},"call":"get_harvested_code_for_paper(arxiv_id=\"2009.14193\")"},{"arxiv_id":"2211.11435","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.11435"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.11435\")"},{"arxiv_id":"2404.11599","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2404.11599"},"call":"get_harvested_code_for_paper(arxiv_id=\"2404.11599\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"874c78aab10e05d636c81aa5f7ef7877b0a67a215546518785b756e5a85a6794","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}