Related papers: Learning Domain-Robust Bioacoustic Representations…
Contrastive learning (CL) has emerged as a powerful paradigm for learning transferable representations without the reliance on large labeled datasets. Its ability to capture intrinsic similarities and differences among data samples has led…
In this work, we propose a novel variational Bayesian adaptive learning approach for cross-domain knowledge transfer to address acoustic mismatches between training and testing conditions, such as recording devices and environmental noise.…
Contrastive learning (CL) has been successful as a powerful representation learning method. In this paper, we propose a contrastive learning framework for cross-domain sentiment classification. We aim to induce domain invariant optimal…
In this work, we study Unsupervised Domain Adaptation (UDA) in a challenging self-supervised approach. One of the difficulties is how to learn task discrimination in the absence of target labels. Unlike previous literature which directly…
Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation . However, most existing SSL methods predict pixels in a single image…
Unsupervised domain adaptation seeks to learn an invariant and discriminative representation for an unlabeled target domain by leveraging the information of a labeled source dataset. We propose to improve the discriminative ability of the…
Methods based on supervised learning using annotations in an end-to-end fashion have been the state-of-the-art for classification problems. However, they may be limited in their generalization capability, especially in the low data regime.…
Self-supervised learning (SSL) algorithms have emerged as powerful tools that can leverage large quantities of unlabeled audio data to pre-train robust representations that support strong performance on diverse downstream tasks. Up to now…
Overarching goals for this work aim to advance the state of the art for detection, classification and localization (DCL) in the field of bioacoustics. This goal is primarily achieved by building a generic framework for…
Deep learning based medical imaging classification models usually suffer from the domain shift problem, where the classification performance drops when training data and real-world data differ in imaging equipment manufacturer, image…
Machine hearing or listening represents an emerging area. Conventional approaches rely on the design of handcrafted features specialized to a specific audio task and that can hardly generalized to other audio fields. For example,…
Learning transferable and domain adaptive feature representations from videos is important for video-relevant tasks such as action recognition. Existing video domain adaptation methods mainly rely on adversarial feature alignment, which has…
During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification…
Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified…
This manuscript presents an approach for multi zone sound field reproduction using supervised learning. Traditional multi zone sound field reproduction methods assume constant speed of sound, neglecting nonlinear effects like wind and…
We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations…
Contrastive learning constitutes an emerging branch of self-supervised learning that leverages large amounts of unlabeled data, by learning a latent space, where pairs of different views of the same sample are associated. In this paper, we…
In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo…
Real-world data often exhibits long tail distributions with heavy class imbalance, where the majority classes can dominate the training process and alter the decision boundaries of the minority classes. Recently, researchers have…
Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain. The conventional DA strategy is to align the feature distributions of the two domains. Recently, increasing…