{"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/eat-self-supervised-pre-training-with","title":"EAT: Self-Supervised Pre-Training with Efficient Audio Transformer","arxiv_id":"2401.03497","date":"2024-01-07","proceeding":null,"authors":["Wenxi Chen","Yuzhe Liang","Ziyang Ma","Zhisheng Zheng","Xie Chen"],"abstract":"Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to the potential application and optimization of audio SSL models. In this paper, inspired by the success of data2vec 2.0 in image modality and Audio-MAE in audio modality, we introduce Efficient Audio Transformer (EAT) to further improve the effectiveness and efficiency in audio SSL. The proposed EAT adopts the bootstrap self-supervised training paradigm to the audio domain. A novel Utterance-Frame Objective (UFO) is designed to enhance the modeling capability of acoustic events. Furthermore, we reveal that the masking strategy is critical in audio SSL pre-training, and superior audio representations can be obtained with large inverse block masks. Experiment results demonstrate that EAT achieves state-of-the-art (SOTA) performance on a range of audio-related tasks, including AudioSet (AS-2M, AS-20K), ESC-50, and SPC-2, along with a significant pre-training speedup up to ~15x compared to existing audio SSL models.","url_abs":"https://arxiv.org/abs/2401.03497v1","url_pdf":"https://arxiv.org/pdf/2401.03497v1.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":"eat-self-supervised-pre-training-with","repo_url":"https://github.com/cwx-worst-one/eat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"sound-classification","task_name":"Sound Classification"}],"methods":[{"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":"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-audioset","task":"Audio Classification","dataset":"AudioSet","model":"EAT","rank_in_archive_order":18,"of":51,"metrics":{"Test mAP":"0.486"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-balanced-audio-set","task":"Audio Classification","dataset":"Balanced Audio Set","model":"EAT","rank_in_archive_order":3,"of":8,"metrics":{"Mean AP":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/audio-classification-on-esc-50","task":"Audio Classification","dataset":"ESC-50","model":"EAT","rank_in_archive_order":15,"of":29,"metrics":{"Accuracy (5-fold)":"96.0","PRE-TRAINING DATASET":"AudioSet","Top-1 Accuracy":"96.0"},"uses_additional_data":true},{"leaderboard":"/sota/audio-classification-on-speech-commands-1","task":"Audio Classification","dataset":"Speech Commands","model":"EAT","rank_in_archive_order":1,"of":7,"metrics":{"Accuracy":"98.3±0.04"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.03497","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03497"}},"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/cwx-worst-one/eat","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":13,"unverified":4},"by_repo_kind":{"official":{"samples":17,"ran":13,"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":"6a3e3a9bf8ae9914","entry":"build_dictionary","repo":"cwx-worst-one/eat","repo_kind":"official","path":"inference/inference.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/inference/inference.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":"6a3e3a9bf8ae9914"}},{"code_sha256_prefix":"66f7af815e734d4e","entry":"compute_block_mask_1d","repo":"cwx-worst-one/eat","repo_kind":"official","path":"utils/data_utils.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/utils/data_utils.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":"66f7af815e734d4e"}},{"code_sha256_prefix":"067591e38407a2be","entry":"compute_block_mask_2d","repo":"cwx-worst-one/eat","repo_kind":"official","path":"utils/data_utils.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/utils/data_utils.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":"067591e38407a2be"}},{"code_sha256_prefix":"c4e0295ea525f219","entry":"compute_mask_indices","repo":"cwx-worst-one/eat","repo_kind":"official","path":"utils/data_utils.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/utils/data_utils.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":"c4e0295ea525f219"}},{"code_sha256_prefix":"22d21a785404efe9","entry":"extract_feature_tensor","repo":"cwx-worst-one/eat","repo_kind":"official","path":"feature_extract/feature_extract.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/feature_extract/feature_extract.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":"22d21a785404efe9"}},{"code_sha256_prefix":"77e8a3ac46f3afec","entry":"get_2d_sincos_pos_embed","repo":"cwx-worst-one/eat","repo_kind":"official","path":"models/mae.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/models/mae.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"77e8a3ac46f3afec"}},{"code_sha256_prefix":"68fc090d0a502993","entry":"get_2d_sincos_pos_embed_flexible","repo":"cwx-worst-one/eat","repo_kind":"official","path":"models/mae.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/models/mae.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":"68fc090d0a502993"}},{"code_sha256_prefix":"5d5be3c7916a67cb","entry":"get_annealed_rate","repo":"cwx-worst-one/eat","repo_kind":"official","path":"models/base.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/models/base.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":"5d5be3c7916a67cb"}},{"code_sha256_prefix":"3f903f847b8f7f28","entry":"get_layer_id_for_vit","repo":"cwx-worst-one/eat","repo_kind":"official","path":"models/EAT_audio_classification.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/models/EAT_audio_classification.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3f903f847b8f7f28"}},{"code_sha256_prefix":"6b945011d5d4e179","entry":"mixup_target","repo":"cwx-worst-one/eat","repo_kind":"official","path":"utils/mixup.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/utils/mixup.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":"6b945011d5d4e179"}},{"code_sha256_prefix":"6caffa789f1bdabe","entry":"one_hot","repo":"cwx-worst-one/eat","repo_kind":"official","path":"utils/mixup.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/utils/mixup.py","link_basis":"harvester_set","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":"6caffa789f1bdabe"}},{"code_sha256_prefix":"3913c620f6926f42","entry":"rand_bbox","repo":"cwx-worst-one/eat","repo_kind":"official","path":"utils/mixup.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/utils/mixup.py","link_basis":"harvester_set","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":"3913c620f6926f42"}},{"code_sha256_prefix":"ee9ac852b4eb7975","entry":"random_masking","repo":"cwx-worst-one/eat","repo_kind":"official","path":"models/base.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/models/base.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":"ee9ac852b4eb7975"}},{"code_sha256_prefix":"3a95f65cb24c84e6","entry":"gather_unmasked","repo":"cwx-worst-one/eat","repo_kind":"official","path":"models/base.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/models/base.py","link_basis":"first_harvest_node","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":"3a95f65cb24c84e6"}},{"code_sha256_prefix":"a663b7a41d863edb","entry":"load_model","repo":"cwx-worst-one/eat","repo_kind":"official","path":"feature_extract/feature_extract.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/feature_extract/feature_extract.py","link_basis":"first_harvest_node","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":"a663b7a41d863edb"}},{"code_sha256_prefix":"31694976f9ae8e78","entry":"load_model","repo":"cwx-worst-one/eat","repo_kind":"official","path":"inference/inference.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/inference/inference.py","link_basis":"first_harvest_node","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":"31694976f9ae8e78"}},{"code_sha256_prefix":"915281feeb90ee5a","entry":"modify_relative_position_bias","repo":"cwx-worst-one/eat","repo_kind":"official","path":"models/mae.py","file_url":"https://github.com/cwx-worst-one/eat/blob/HEAD/models/mae.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":"915281feeb90ee5a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}