Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models
Recently, pre-trained models for music information retrieval based on self-supervised learning (SSL) are becoming popular, showing success in various downstream tasks. However, there is limited research on the specific meanings of the encoded information and their applicability. Exploring these aspects can help us better understand their capabilities and limitations, leading to more effective use in downstream tasks. In this study, we analyze the advanced music representation model MusicFM and the newly emerged SSL model MuQ. We focus on three main aspects: (i) validating the advantages of SSL models across multiple downstream tasks, (ii) exploring the specialization of layer-wise information for different tasks, and (iii) comparing performance differences when selecting specific layers. Through this analysis, we reveal insights into the structure and potential applications of SSL models in music information retrieval.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalMusic Information RetrievalRetrievalSelf-Supervised LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Multi-scale Unified Network for Image Classification
Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real…
ClassificationComputational Efficiencyimage-classificationImage Classification+1Towards Federated Learning Under Resource Constraints via Layer-wise Training and Depth Dropout
Large machine learning models trained on diverse data have recently seen unprecedented success. Federated learning enables training on private data that may otherwise be inaccessible, such as domain-specific datasets dec…
Federated LearningRepresentation LearningSelf-Supervised LearningSimplified Self-Attention for Transformer-based End-to-End Speech Recognition
Transformer models have been introduced into end-to-end speech recognition with state-of-the-art performance on various tasks owing to their superiority in modeling long-term dependencies. However, such improvements are …
speech-recognitionSpeech RecognitionDeep Attention-guided Graph Clustering with Dual Self-supervision
Existing deep embedding clustering works only consider the deepest layer to learn a feature embedding and thus fail to well utilize the available discriminative information from cluster assignments, resulting performance…
ClusteringDeep AttentionGraph ClusteringTripletBlockwise Self-Supervised Learning at Scale
Current state-of-the-art deep networks are all powered by backpropagation. In this paper, we explore alternatives to full backpropagation in the form of blockwise learning rules, leveraging the latest developments in sel…
Self-Supervised Learning