Related papers: Self-supervised EEG Representation Learning for Au…

Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because…

We propose PARSE, a novel semi-supervised architecture for learning strong EEG representations for emotion recognition. To reduce the potential distribution mismatch between the large amounts of unlabeled data and the limited amount of…

Self-supervised learning has proven to be an effective way to learn representations in domains where annotated labels are scarce, such as medical imaging. A widely adopted framework for this purpose is contrastive learning and it has been…

We present and evaluate the capacity of a deep neural network to learn robust features from EEG to automatically detect seizures. This is a challenging problem because seizure manifestations on EEG are extremely variable both inter- and…

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…

Since convolutional neural networks (CNNs) can easily overfit noisy labels, which are ubiquitous in visual classification tasks, it has been a great challenge to train CNNs against them robustly. Various methods have been proposed for this…

Sentence embeddings are an important component of many natural language processing (NLP) systems. Like word embeddings, sentence embeddings are typically learned on large text corpora and then transferred to various downstream tasks, such…

We propose a novel self-supervised approach for learning audio and visual representations from unlabeled videos, based on their correspondence. The approach uses an attention mechanism to learn the relative importance of convolutional…

As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often…

EEG signals have been reported to be informative and reliable for emotion recognition in recent years. However, the inter-subject variability of emotion-related EEG signals still poses a great challenge for the practical applications of…

The availability of clean and diverse labeled data is a major roadblock for training models on complex tasks such as visual question answering (VQA). The extensive work on large vision-and-language models has shown that self-supervised…

Environmental Sound Classification (ESC) is a challenging field of research in non-speech audio processing. Most of current research in ESC focuses on designing deep models with special architectures tailored for specific audio datasets,…

Sleep studies are important for diagnosing sleep disorders such as insomnia, narcolepsy or sleep apnea. They rely on manual scoring of sleep stages from raw polisomnography signals, which is a tedious visual task requiring the workload of…

In recent years, self-supervised learning methods have shown significant improvement for pre-training with unlabeled data and have proven helpful for electrocardiogram signals. However, most previous pre-training methods for…

Biological measurements are often contaminated with large amounts of non-stationary noise which require effective noise reduction techniques. We present a new real-time deep learning algorithm which produces adaptively a signal opposing the…

To improve performance in visual feature representation from photos or videos for practical applications, we generally require large-scale human-annotated labeled data while training deep neural networks. However, the cost of gathering and…

Electroencephalography (EEG) reflects the brain's functional state, making it a crucial tool for diverse detection applications like seizure detection and sleep stage classification. While deep learning-based approaches have recently shown…

Graph representation learning has attracted lots of attention recently. Existing graph neural networks fed with the complete graph data are not scalable due to limited computation and memory costs. Thus, it remains a great challenge to…

Deep learning has shown impressive results in reducing noise and artifacts in X-ray computed tomography (CT) reconstruction. Self-supervised CT reconstruction methods are especially appealing for real-world applications because they require…

Recently, self-supervised learning has attracted attention due to its remarkable ability to acquire meaningful representations for classification tasks without using semantic labels. This paper introduces a self-supervised learning…