{"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/film-ensemble-probabilistic-deep-learning-via","title":"FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation","arxiv_id":"2206.00050","date":"2022-05-31","proceeding":null,"authors":["Mehmet Ozgur Turkoglu","Alexander Becker","Hüseyin Anil Gündüz","Mina Rezaei","Bernd Bischl","Rodrigo Caye Daudt","Stefano D'Aronco","Jan Dirk Wegner","Konrad Schindler"],"abstract":"The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncertainty predictions. A common approach to quantify epistemic uncertainty, usable across a wide class of prediction models, is to train a model ensemble. In a naive implementation, the ensemble approach has high computational cost and high memory demand. This challenges in particular modern deep learning, where even a single deep network is already demanding in terms of compute and memory, and has given rise to a number of attempts to emulate the model ensemble without actually instantiating separate ensemble members. We introduce FiLM-Ensemble, a deep, implicit ensemble method based on the concept of Feature-wise Linear Modulation (FiLM). That technique was originally developed for multi-task learning, with the aim of decoupling different tasks. We show that the idea can be extended to uncertainty quantification: by modulating the network activations of a single deep network with FiLM, one obtains a model ensemble with high diversity, and consequently well-calibrated estimates of epistemic uncertainty, with low computational overhead in comparison. Empirically, FiLM-Ensemble outperforms other implicit ensemble methods, and it and comes very close to the upper bound of an explicit ensemble of networks (sometimes even beating it), at a fraction of the memory cost.","url_abs":"https://arxiv.org/abs/2206.00050v4","url_pdf":"https://arxiv.org/pdf/2206.00050v4.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":"film-ensemble-probabilistic-deep-learning-via","repo_url":"https://github.com/prs-eth/film-ensemble","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"probabilistic-deep-learning","task_name":"Probabilistic Deep Learning"},{"task_slug":"uncertainty-quantification","task_name":"Uncertainty Quantification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2206.00050","atlas_url":"https://app.syntology.ai/?focus=2206.00050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00050"}},"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/prs-eth/film-ensemble","reach":null}],"summary":{"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"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":"1542db8591929a16","entry":"CBN2D","repo":"prs-eth/film-ensemble","repo_kind":"official","path":"models/resnet_film.py","file_url":"https://github.com/prs-eth/film-ensemble/blob/HEAD/models/resnet_film.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1542db8591929a16"}},{"code_sha256_prefix":"4ab3fe84516b2a14","entry":"ResNet18_FILM","repo":"prs-eth/FILM-Ensemble","repo_kind":"official","path":"models/resnet_film.py","file_url":"https://github.com/prs-eth/FILM-Ensemble/blob/HEAD/models/resnet_film.py","link_basis":"first_harvest_node","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":"4ab3fe84516b2a14"}},{"code_sha256_prefix":"bb20ffc29b591dbf","entry":"ResNet34_FILM","repo":"prs-eth/FILM-Ensemble","repo_kind":"official","path":"models/resnet_film.py","file_url":"https://github.com/prs-eth/FILM-Ensemble/blob/HEAD/models/resnet_film.py","link_basis":"first_harvest_node","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":"bb20ffc29b591dbf"}},{"code_sha256_prefix":"d84555586acff92a","entry":"ResNet50_FILM","repo":"prs-eth/FILM-Ensemble","repo_kind":"official","path":"models/resnet_film.py","file_url":"https://github.com/prs-eth/FILM-Ensemble/blob/HEAD/models/resnet_film.py","link_basis":"first_harvest_node","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":"d84555586acff92a"}},{"code_sha256_prefix":"263d215e8e804b14","entry":"ResNet_FILM","repo":"prs-eth/film-ensemble","repo_kind":"official","path":"models/resnet_film.py","file_url":"https://github.com/prs-eth/film-ensemble/blob/HEAD/models/resnet_film.py","link_basis":"first_harvest_node","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":"263d215e8e804b14"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}