On the Transferability of Large-Scale Self-Supervision to Few-Shot Audio Classification

2024-02-02 · Calum Heggan, Sam Budgett, Timothy Hospedales, Mehrdad Yaghoobi

In recent years, self-supervised learning has excelled for its capacity to learn robust feature representations from unlabelled data. Networks pretrained through self-supervision serve as effective feature extractors for downstream tasks, including Few-Shot Learning. While the evaluation of unsupervised approaches for few-shot learning is well-established in imagery, it is notably absent in acoustics. This study addresses this gap by assessing large-scale self-supervised models' performance in few-shot audio classification. Additionally, we explore the relationship between a model's few-shot learning capability and other downstream task benchmarks. Our findings reveal state-of-the-art performance in some few-shot problems such as SpeechCommandsv2, as well as strong correlations between speech-based few-shot problems and various downstream audio tasks.

📄 PDF Abstract BibTeX arXiv:2402.01274

Code (1)

CHeggan/Few-Shot-Classification-for-Audio-Evaluation pytorch

Tasks

Audio Classification Few-Shot Audio Classification Few-Shot Learning Self-Supervised Learning

Boosting Supervision with Self-Supervision for Few-shot Learning

2019-06-17 · Jong-Chyi Su, Subhransu Maji, Bharath Hariharan

We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervise…

Few-Shot Learning Self-Supervised Learning

Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

2021-10-11 · ICLR 2022 4 · Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui 외

Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP…

Zero-Shot Learning

GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs

2024-10-14 · Yun Zhu, Haizhou Shi, Xiaotang Wang, Yongchao Liu 외

Recently, research on Text-Attributed Graphs (TAGs) has gained significant attention due to the prevalence of free-text node features in real-world applications and the advancements in Large Language Models (LLMs) that b…

Few-Shot Learning TAG

Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment

2025-09-11 · Dimitrios Anastasiou, Razvan Caramalau, Nazir Sirajudeen, Matthew Boal 외 arxiv

Automated surgical skill assessment (SSA) is a central task in surgical computer vision. Developing robust SSA models is challenging due to the scarcity of skill annotations, which are time-consuming to produce and requi…

Few-Shot Learning

Shot in the Dark: Few-Shot Learning with No Base-Class Labels

2020-10-06 · Zitian Chen, Subhransu Maji, Erik Learned-Miller

Few-shot learning aims to build classifiers for new classes from a small number of labeled examples and is commonly facilitated by access to examples from a distinct set of 'base classes'. The difference in data distribu…

Few-Shot Learning Inductive Bias Self-Supervised Learning Unsupervised Few-Shot Image Classification+1