{"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/efficient-large-scale-audio-tagging-via","title":"Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation","arxiv_id":"2211.04772","date":"2022-11-09","proceeding":null,"authors":["Florian Schmid","Khaled Koutini","Gerhard Widmer"],"abstract":"Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority is based on the ability to scale up and exploit large-scale datasets such as AudioSet. However, Transformers are demanding in terms of model size and computational requirements compared to CNNs. We propose a training procedure for efficient CNNs based on offline Knowledge Distillation (KD) from high-performing yet complex transformers. The proposed training schema and the efficient CNN design based on MobileNetV3 results in models outperforming previous solutions in terms of parameter and computational efficiency and prediction performance. We provide models of different complexity levels, scaling from low-complexity models up to a new state-of-the-art performance of .483 mAP on AudioSet. Source Code available at: https://github.com/fschmid56/EfficientAT","url_abs":"https://arxiv.org/abs/2211.04772v3","url_pdf":"https://arxiv.org/pdf/2211.04772v3.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":"efficient-large-scale-audio-tagging-via","repo_url":"https://github.com/fschmid56/efficientat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"efficient-large-scale-audio-tagging-via","repo_url":"https://github.com/fschmid56/efficientat_hear","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"audio-tagging","task_name":"Audio Tagging"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"hard-swish","method_name":"Hard Swish"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"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":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"relu6","method_name":"ReLU6"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeeze-and-excitation-block","method_name":"Squeeze-and-Excitation Block"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-audioset","task":"Audio Classification","dataset":"AudioSet","model":"mn40_as (Ensemble)","rank_in_archive_order":10,"of":51,"metrics":{"Test mAP":"0.498"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-audioset","task":"Audio Classification","dataset":"AudioSet","model":"mn40_as (Single)","rank_in_archive_order":24,"of":51,"metrics":{"Test mAP":"0.483"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-esc-50","task":"Audio Classification","dataset":"ESC-50","model":"mn40_as","rank_in_archive_order":6,"of":29,"metrics":{"Accuracy (5-fold)":"97.45","PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"97.45"},"uses_additional_data":true},{"leaderboard":"/sota/audio-tagging-on-audioset","task":"Audio Tagging","dataset":"AudioSet","model":"mn40_as (Ensemble)","rank_in_archive_order":2,"of":11,"metrics":{"mean average precision":"0.498"},"uses_additional_data":true},{"leaderboard":"/sota/audio-tagging-on-audioset","task":"Audio Tagging","dataset":"AudioSet","model":"mn40_as (Single)","rank_in_archive_order":6,"of":11,"metrics":{"mean average precision":"0.483"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.04772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.04772"}},"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/fschmid56/efficientat","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fschmid56/efficientat_hear","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"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":"4e582be02ea360fa","entry":"get_scene_embeddings","repo":"fschmid56/efficientat_hear","repo_kind":"listed","path":"hear_mn/mn01_all_b_avg_max_time_pool.py","file_url":"https://github.com/fschmid56/efficientat_hear/blob/HEAD/hear_mn/mn01_all_b_avg_max_time_pool.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e582be02ea360fa"}},{"code_sha256_prefix":"0e956046855f5a5e","entry":"get_timestamp_embeddings","repo":"fschmid56/efficientat_hear","repo_kind":"listed","path":"hear_mn/mn01_all_b_avg_max_time_pool.py","file_url":"https://github.com/fschmid56/efficientat_hear/blob/HEAD/hear_mn/mn01_all_b_avg_max_time_pool.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":"0e956046855f5a5e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}