{"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/learning-from-between-class-examples-for-deep","title":"Learning from Between-class Examples for Deep Sound Recognition","arxiv_id":"1711.10282","date":"2017-11-28","proceeding":"ICLR 2018 1","authors":["Yuji Tokozume","Yoshitaka Ushiku","Tatsuya Harada"],"abstract":"Deep learning methods have achieved high performance in sound recognition\ntasks. Deciding how to feed the training data is important for further\nperformance improvement. We propose a novel learning method for deep sound\nrecognition: Between-Class learning (BC learning). Our strategy is to learn a\ndiscriminative feature space by recognizing the between-class sounds as\nbetween-class sounds. We generate between-class sounds by mixing two sounds\nbelonging to different classes with a random ratio. We then input the mixed\nsound to the model and train the model to output the mixing ratio. The\nadvantages of BC learning are not limited only to the increase in variation of\nthe training data; BC learning leads to an enlargement of Fisher's criterion in\nthe feature space and a regularization of the positional relationship among the\nfeature distributions of the classes. The experimental results show that BC\nlearning improves the performance on various sound recognition networks,\ndatasets, and data augmentation schemes, in which BC learning proves to be\nalways beneficial. Furthermore, we construct a new deep sound recognition\nnetwork (EnvNet-v2) and train it with BC learning. As a result, we achieved a\nperformance surpasses the human level.","url_abs":"http://arxiv.org/abs/1711.10282v2","url_pdf":"http://arxiv.org/pdf/1711.10282v2.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":"learning-from-between-class-examples-for-deep","repo_url":"https://github.com/mil-tokyo/bc_learning_sound","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"learning-from-between-class-examples-for-deep","repo_url":"https://github.com/HaoranREN/EnvNet_v1_v2_TensorFlow_Keras","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-from-between-class-examples-for-deep","repo_url":"https://github.com/Splinter0/CoughCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-from-between-class-examples-for-deep","repo_url":"https://github.com/mil-tokyo/bc_learning_image","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"learning-from-between-class-examples-for-deep","repo_url":"https://github.com/mohaimenz/EnvNet-V2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.10282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10282"}},"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/mohaimenz/EnvNet-V2","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mil-tokyo/bc_learning_image","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HaoranREN/EnvNet_v1_v2_TensorFlow_Keras","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mil-tokyo/bc_learning_sound","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Splinter0/CoughCNN","reach":{"status":"ok"}}],"summary":{"ran_honours":1},"by_repo_kind":{"listed":{"samples":1,"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":1,"samples":[{"code_sha256_prefix":"27341ddedfdb004b","entry":"lr_schedule","repo":"HaoranREN/EnvNet_v1_v2_TensorFlow_Keras","repo_kind":"listed","path":"EnvNet_v2.py","file_url":"https://github.com/HaoranREN/EnvNet_v1_v2_TensorFlow_Keras/blob/HEAD/EnvNet_v2.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"27341ddedfdb004b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}