Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning

• URL: http://arxiv.org/abs/2502.12031v1
• Date: Mon, 17 Feb 2025 17:02:26 GMT
• Title: Masked Latent Prediction and Classification for Self-Supervised Audio Representation Learning
• Authors: Aurian Quelennec, Pierre Chouteau, Geoffroy Peeters, Slim Essid,
• Abstract summary: We propose a new method: MAsked latenT Prediction And Classification (MATPAC), which is trained with two pretext tasks solved jointly. MATPAC reaches state-of-the-art self-supervised learning results on reference audio classification datasets such as OpenMIC, GTZAN, ESC-50 and US8K.
• Score: 9.580895202050947
• License:
• Abstract: Recently, self-supervised learning methods based on masked latent prediction have proven to encode input data into powerful representations. However, during training, the learned latent space can be further transformed to extract higher-level information that could be more suited for downstream classification tasks. Therefore, we propose a new method: MAsked latenT Prediction And Classification (MATPAC), which is trained with two pretext tasks solved jointly. As in previous work, the first pretext task is a masked latent prediction task, ensuring a robust input representation in the latent space. The second one is unsupervised classification, which utilises the latent representations of the first pretext task to match probability distributions between a teacher and a student. We validate the MATPAC method by comparing it to other state-of-the-art proposals and conducting ablations studies. MATPAC reaches state-of-the-art self-supervised learning results on reference audio classification datasets such as OpenMIC, GTZAN, ESC-50 and US8K and outperforms comparable supervised methods results for musical auto-tagging on Magna-tag-a-tune.

Related papers

• Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts [104.9871176044644]
  Masked Autoencoder(MAE) is a prevailing self-supervised learning method that achieves promising results in model pre-training. We propose a novel MAE-based pre-training paradigm, Mixture of Cluster-conditional Experts (MoCE) MoCE trains each expert only with semantically relevant images by using cluster-conditional gates.
  arXiv  Detail & Related papers  (2024-02-08T03:46:32Z)
• DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer [6.898332152137321]
  Unsupervised dense semantic segmentation has not been explored as a downstream task. This paper proposes a novel data-driven approach for unsupervised semantic segmentation as a downstream task. Best version of DatUS2 outperforms the existing state-of-the-art method for the unsupervised dense semantic segmentation task.
  arXiv  Detail & Related papers  (2024-01-23T14:53:32Z)
• Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [56.092059713922744]
  We show that using high-level contextualized features as prediction targets can achieve superior performance. Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework. Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2024-01-01T12:08:35Z)
• Multi-Level Contrastive Learning for Dense Prediction Task [59.591755258395594]
  We present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three key factors in detection: localization, scale consistency and recognition. Our method consistently outperforms the recent state-of-the-art methods on various datasets with significant margins.
  arXiv  Detail & Related papers  (2023-04-04T17:59:04Z)
• Enhancing Deep Knowledge Tracing with Auxiliary Tasks [24.780533765606922]
  We propose emphAT-DKT to improve the prediction performance of the original deep knowledge tracing model. We conduct comprehensive experiments on three real-world educational datasets and compare the proposed approach to both deep sequential KT models and non-sequential models.
  arXiv  Detail & Related papers  (2023-02-14T08:21:37Z)
• Class Token and Knowledge Distillation for Multi-head Self-Attention Speaker Verification Systems [20.55054374525828]
  This paper explores three novel approaches to improve the performance of speaker verification systems based on deep neural networks (DNN) Firstly, we propose the use of a learnable vector called Class token to replace the average global pooling mechanism to extract the embeddings. Second, we have added a distilled representation token for training a teacher-student pair of networks using the Knowledge Distillation (KD) philosophy.
  arXiv  Detail & Related papers  (2021-11-06T09:47:05Z)
• Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [101.28281124670647]
  Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. We propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning. Our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.
  arXiv  Detail & Related papers  (2021-08-12T09:14:44Z)
• Predicting What You Already Know Helps: Provable Self-Supervised Learning [60.27658820909876]
  Self-supervised representation learning solves auxiliary prediction tasks (known as pretext tasks) without requiring labeled data. We show a mechanism exploiting the statistical connections between certain em reconstruction-based pretext tasks that guarantee to learn a good representation. We prove the linear layer yields small approximation error even for complex ground truth function class.
  arXiv  Detail & Related papers  (2020-08-03T17:56:13Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.