{"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/ambient-sound-provides-supervision-for-visual","title":"Ambient Sound Provides Supervision for Visual Learning","arxiv_id":"1608.07017","date":"2016-08-25","proceeding":null,"authors":["Andrew Owens","Jiajun Wu","Josh H. McDermott","William T. Freeman","Antonio Torralba"],"abstract":"The sound of crashing waves, the roar of fast-moving cars -- sound conveys\nimportant information about the objects in our surroundings. In this work, we\nshow that ambient sounds can be used as a supervisory signal for learning\nvisual models. To demonstrate this, we train a convolutional neural network to\npredict a statistical summary of the sound associated with a video frame. We\nshow that, through this process, the network learns a representation that\nconveys information about objects and scenes. We evaluate this representation\non several recognition tasks, finding that its performance is comparable to\nthat of other state-of-the-art unsupervised learning methods. Finally, we show\nthrough visualizations that the network learns units that are selective to\nobjects that are often associated with characteristic sounds.","url_abs":"http://arxiv.org/abs/1608.07017v2","url_pdf":"http://arxiv.org/pdf/1608.07017v2.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":"ambient-sound-provides-supervision-for-visual","repo_url":"https://github.com/rowhanm/ambient-sound-self-supervision","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-recognition","task_name":"Object Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.07017","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.07017"}},"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/rowhanm/ambient-sound-self-supervision","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":12},"by_repo_kind":{"listed":{"samples":13,"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":"3e21e6589663b136","entry":"epoch_time","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"pretext_training/pretext_train_5_alexnet.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/pretext_training/pretext_train_5_alexnet.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e21e6589663b136"}},{"code_sha256_prefix":"4d3faaaa1c706b0b","entry":"accuracy","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"downstream_evaluation/finetune_voc.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/downstream_evaluation/finetune_voc.py","link_basis":"harvester_set","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":"4d3faaaa1c706b0b"}},{"code_sha256_prefix":"170624d53a903496","entry":"alexnet","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"utils/models.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/utils/models.py","link_basis":"harvester_set","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":"170624d53a903496"}},{"code_sha256_prefix":"2789ed37f7a2637e","entry":"calculate_accuracy","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"pretext_training/pretext_train_5_alexnet.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/pretext_training/pretext_train_5_alexnet.py","link_basis":"harvester_set","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":"2789ed37f7a2637e"}},{"code_sha256_prefix":"d7e0681d7b94b304","entry":"deprocess_image","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"downstream_evaluation/grad_ascent.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/downstream_evaluation/grad_ascent.py","link_basis":"harvester_set","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":"d7e0681d7b94b304"}},{"code_sha256_prefix":"62a90a990e18bc83","entry":"draw_on","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"utils/aolib_img.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/utils/aolib_img.py","link_basis":"harvester_set","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":"62a90a990e18bc83"}},{"code_sha256_prefix":"84d949f774e2ca7b","entry":"evaluate","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"pretext_training/pretext_train_5_alexnet.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/pretext_training/pretext_train_5_alexnet.py","link_basis":"harvester_set","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":"84d949f774e2ca7b"}},{"code_sha256_prefix":"c9706c092718039b","entry":"freq2erb","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"pretext_training/get_statistical_summaries.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/pretext_training/get_statistical_summaries.py","link_basis":"harvester_set","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":"c9706c092718039b"}},{"code_sha256_prefix":"3abf2c16454d0592","entry":"load_model","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"downstream_evaluation/ft_util.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/downstream_evaluation/ft_util.py","link_basis":"harvester_set","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":"3abf2c16454d0592"}},{"code_sha256_prefix":"68d8bd2d7e4d0e88","entry":"make_layers_features","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"utils/models.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/utils/models.py","link_basis":"harvester_set","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":"68d8bd2d7e4d0e88"}},{"code_sha256_prefix":"5f3cccf706a6e319","entry":"rename_key","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"downstream_evaluation/finetune_voc.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/downstream_evaluation/finetune_voc.py","link_basis":"harvester_set","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":"5f3cccf706a6e319"}},{"code_sha256_prefix":"aa0b8fa1809385c5","entry":"sound_from_subbands","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"pretext_training/get_statistical_summaries.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/pretext_training/get_statistical_summaries.py","link_basis":"harvester_set","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":"aa0b8fa1809385c5"}},{"code_sha256_prefix":"716d4bc48005dd53","entry":"subbands_from_sound","repo":"rowhanm/ambient-sound-self-supervision","repo_kind":"listed","path":"pretext_training/get_statistical_summaries.py","file_url":"https://github.com/rowhanm/ambient-sound-self-supervision/blob/HEAD/pretext_training/get_statistical_summaries.py","link_basis":"harvester_set","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":"716d4bc48005dd53"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}