{"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-visual-reasoning-with-a-general","title":"FiLM: Visual Reasoning with a General Conditioning Layer","arxiv_id":"1709.07871","date":"2017-09-22","proceeding":null,"authors":["Ethan Perez","Florian Strub","Harm de Vries","Vincent Dumoulin","Aaron Courville"],"abstract":"We introduce a general-purpose conditioning method for neural networks called\nFiLM: Feature-wise Linear Modulation. FiLM layers influence neural network\ncomputation via a simple, feature-wise affine transformation based on\nconditioning information. We show that FiLM layers are highly effective for\nvisual reasoning - answering image-related questions which require a\nmulti-step, high-level process - a task which has proven difficult for standard\ndeep learning methods that do not explicitly model reasoning. Specifically, we\nshow on visual reasoning tasks that FiLM layers 1) halve state-of-the-art error\nfor the CLEVR benchmark, 2) modulate features in a coherent manner, 3) are\nrobust to ablations and architectural modifications, and 4) generalize well to\nchallenging, new data from few examples or even zero-shot.","url_abs":"http://arxiv.org/abs/1709.07871v2","url_pdf":"http://arxiv.org/pdf/1709.07871v2.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-visual-reasoning-with-a-general","repo_url":"https://github.com/ethanjperez/film","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"film-visual-reasoning-with-a-general","repo_url":"https://github.com/CPJKU/audio_conditioned_unet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"film-visual-reasoning-with-a-general","repo_url":"https://github.com/GuessWhatGame/clevr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"film-visual-reasoning-with-a-general","repo_url":"https://github.com/caffeinism/film-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"film-visual-reasoning-with-a-general","repo_url":"https://github.com/jjgo/hyperlight","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"film-visual-reasoning-with-a-general","repo_url":"https://github.com/kdaip/stabletts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"film-visual-reasoning-with-a-general","repo_url":"https://github.com/keonlee9420/Daft-Exprt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-modal","task_name":"Image Retrieval with Multi-Modal Query"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"visual-question-answering-vqa-split-a","task_name":"Visual Question Answering (VQA) Split A"},{"task_slug":"visual-question-answering-vqa-split-b","task_name":"Visual Question Answering (VQA) Split B"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-retrieval-with-multi-modal-query-on-mit","task":"Image Retrieval with Multi-Modal Query","dataset":"MIT-States","model":"FiLM","rank_in_archive_order":4,"of":5,"metrics":{"Recall@1":"10.1","Recall@10":"38.3","Recall@5":"27.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-clevr","task":"Visual Question Answering (VQA)","dataset":"CLEVR","model":"CNN+GRU+FiLM","rank_in_archive_order":11,"of":15,"metrics":{"Accuracy":"97.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-clevr-humans","task":"Visual Question Answering (VQA)","dataset":"CLEVR-Humans","model":"CNN+GRU+FiLM","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"75.9"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1709.07871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.07871"}},"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":"deterministic:regex_extraction","url":"https://github.com/ethanjperez/film","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GuessWhatGame/clevr","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jjgo/hyperlight","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kdaip/stabletts","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keonlee9420/Daft-Exprt","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/caffeinism/film-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CPJKU/audio_conditioned_unet","reach":null}],"summary":{"ran":8,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"listed":{"samples":9,"ran":8,"repositories":4}},"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":7,"samples":[{"code_sha256_prefix":"37dda49b6caaba23","entry":"Classifier","repo":"caffeinism/film-pytorch","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/caffeinism/film-pytorch/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"37dda49b6caaba23"}},{"code_sha256_prefix":"edbfcccbabd461c6","entry":"FeatureExtractor","repo":"caffeinism/film-pytorch","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/caffeinism/film-pytorch/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"edbfcccbabd461c6"}},{"code_sha256_prefix":"bc5a2b1350c91ae2","entry":"FiLM","repo":"keonlee9420/Daft-Exprt","repo_kind":"listed","path":"model/blocks.py","file_url":"https://github.com/keonlee9420/Daft-Exprt/blob/HEAD/model/blocks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bc5a2b1350c91ae2"}},{"code_sha256_prefix":"bd2e6b10e2f47993","entry":"FiLM","repo":"CPJKU/audio_conditioned_unet","repo_kind":"listed","path":"audio_conditioned_unet/network.py","file_url":"https://github.com/CPJKU/audio_conditioned_unet/blob/HEAD/audio_conditioned_unet/network.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":"bd2e6b10e2f47993"}},{"code_sha256_prefix":"b8723266db5e5556","entry":"FiLM","repo":"ethanjperez/film","repo_kind":"official","path":"vr/models/filmed_net.py","file_url":"https://github.com/ethanjperez/film/blob/HEAD/vr/models/filmed_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b8723266db5e5556"}},{"code_sha256_prefix":"32874c063a45b37a","entry":"FiLMBlock","repo":"caffeinism/film-pytorch","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/caffeinism/film-pytorch/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32874c063a45b37a"}},{"code_sha256_prefix":"04d3db3a0eb24a12","entry":"FiLMLayer","repo":"kdaip/stabletts","repo_kind":"listed","path":"models/estimator.py","file_url":"https://github.com/kdaip/stabletts/blob/HEAD/models/estimator.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":"04d3db3a0eb24a12"}},{"code_sha256_prefix":"779ef9590306ac85","entry":"ResBlock","repo":"caffeinism/film-pytorch","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/caffeinism/film-pytorch/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"779ef9590306ac85"}},{"code_sha256_prefix":"b4a8caf47616fa06","entry":"conv","repo":"caffeinism/film-pytorch","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/caffeinism/film-pytorch/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4a8caf47616fa06"}},{"code_sha256_prefix":"6d21918b730bc046","entry":"FiLM","repo":"caffeinism/film-pytorch","repo_kind":"listed","path":"networks.py","file_url":"https://github.com/caffeinism/film-pytorch/blob/HEAD/networks.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6d21918b730bc046"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}