{"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/adversarial-fine-tuning-using-generated","title":"Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance","arxiv_id":"2311.06480","date":"2023-11-11","proceeding":null,"authors":["June-Woo Kim","Chihyeon Yoon","Miika Toikkanen","Sangmin Bae","Ho-Young Jung"],"abstract":"Deep generative models have emerged as a promising approach in the medical image domain to address data scarcity. However, their use for sequential data like respiratory sounds is less explored. In this work, we propose a straightforward approach to augment imbalanced respiratory sound data using an audio diffusion model as a conditional neural vocoder. We also demonstrate a simple yet effective adversarial fine-tuning method to align features between the synthetic and real respiratory sound samples to improve respiratory sound classification performance. Our experimental results on the ICBHI dataset demonstrate that the proposed adversarial fine-tuning is effective, while only using the conventional augmentation method shows performance degradation. Moreover, our method outperforms the baseline by 2.24% on the ICBHI Score and improves the accuracy of the minority classes up to 26.58%. For the supplementary material, we provide the code at https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound.","url_abs":"https://arxiv.org/abs/2311.06480v1","url_pdf":"https://arxiv.org/pdf/2311.06480v1.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":"adversarial-fine-tuning-using-generated","repo_url":"https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"sound-classification","task_name":"Sound Classification"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-icbhi-respiratory","task":"Audio Classification","dataset":"ICBHI Respiratory Sound Database","model":"AFT on Mixed-500","rank_in_archive_order":10,"of":25,"metrics":{"ICBHI Score":"61.79","Sensitivity":"42.86","Specificity":"80.72"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.06480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.06480"}},"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/kaen2891/adversarial_","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound","reach":null}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"27f155774bc3357e","entry":"DiffWave","repo":"kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound","repo_kind":"official","path":"Diffwave/model.py","file_url":"https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound/blob/HEAD/Diffwave/model.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":"27f155774bc3357e"}},{"code_sha256_prefix":"7173ee08aff4e2ba","entry":"DiffusionEmbedding","repo":"kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound","repo_kind":"official","path":"Diffwave/model.py","file_url":"https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound/blob/HEAD/Diffwave/model.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":"7173ee08aff4e2ba"}},{"code_sha256_prefix":"4e31c57720333e35","entry":"ResidualBlock","repo":"kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound","repo_kind":"official","path":"Diffwave/model.py","file_url":"https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound/blob/HEAD/Diffwave/model.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":"4e31c57720333e35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}