Related papers: Stethoscope-guided Supervised Contrastive Learning…

Ambiguities in data and problem constraints can lead to diverse, equally plausible outcomes for a machine learning task. In beat and downbeat tracking, for instance, different listeners may adopt various rhythmic interpretations, none of…

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…

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…

Test-time adaptation is a special setting of unsupervised domain adaptation where a trained model on the source domain has to adapt to the target domain without accessing source data. We propose a novel way to leverage self-supervised…

Deep convolutional neural networks have considerably improved state-of-the-art results for semantic segmentation. Nevertheless, even modern architectures lack the ability to generalize well to a test dataset that originates from a different…

Self-supervised pre-training with contrastive learning is a powerful method for learning from sparsely labeled data. However, performance can drop considerably when there is a shift in the distribution of data from training to test time. We…

Linking sheet music images to audio recordings remains a key problem for the development of efficient cross-modal music retrieval systems. One of the fundamental approaches toward this task is to learn a cross-modal embedding space via deep…

With the ongoing development of deep learning, an increasing number of AI models have surpassed the performance levels of human clinical practitioners. However, the prevalence of AI diagnostic products in actual clinical practice remains…

Negative transfer in training of acoustic models for automatic speech recognition has been reported in several contexts such as domain change or speaker characteristics. This paper proposes a novel technique to overcome negative transfer by…

Self-supervised learning (SSL) approaches have achieved great success when the amount of labeled data is limited. Within SSL, models learn robust feature representations by solving pretext tasks. One such pretext task is contrastive…

A complex combination of simultaneous supervised-unsupervised learning is believed to be the key to humans performing tasks seamlessly across multiple domains or tasks. This phenomenon of cross-domain learning has been very well studied in…

The success of deep learning has set new benchmarks for many medical image analysis tasks. However, deep models often fail to generalize in the presence of distribution shifts between training (source) data and test (target) data. One…

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…

Limited availability of labeled physiological data often prohibits the use of powerful supervised deep learning models in the biomedical machine intelligence domain. We approach this problem and propose a novel encoding framework that…

Unsupervised domain adaptation techniques, extensively studied in hyperspectral image (HSI) classification, aim to use labeled source domain data and unlabeled target domain data to learn domain invariant features for cross-scene…

Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source…

Single source domain generalization (SDG) holds promise for more reliable and consistent image segmentation across real-world clinical settings particularly in the medical domain, where data privacy and acquisition cost constraints often…

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

We introduce COLA, a self-supervised pre-training approach for learning a general-purpose representation of audio. Our approach is based on contrastive learning: it learns a representation which assigns high similarity to audio segments…

This paper presents and explores a robust deep learning framework for auscultation analysis. This aims to classify anomalies in respiratory cycles and detect disease, from respiratory sound recordings. The framework begins with front-end…