Related papers: Deep Models for Engagement Assessment With Scarce …
Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity. Active learning is one way to address the challenge of scarce labeled data in practice, by dynamically collecting the…
Researchers have reported high decoding accuracy (>95%) using non-invasive Electroencephalogram (EEG) signals for brain-computer interface (BCI) decoding tasks like image decoding, emotion recognition, auditory spatial attention detection,…
Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…
Transformer neural networks require a large amount of labeled data to train effectively. Such data is often scarce in electroencephalography, as annotations made by medical experts are costly. This is why self-supervised training, using…
Reliable detection of event-related potentials (ERPs) at the single-trial level remains a major challenge due to the low signal-to-noise ratio EEG recordings. In this work, we investigate whether incorporating prior knowledge about ERP…
Modeling engagement in collaborative learning remains challenging, especially in technology-enhanced environments where surface indicators such as participation frequency can be misleading. This study proposes a lightweight and…
Labeling data (e.g., labeling the people, objects, actions and scene in images) comprehensively and efficiently is a widely needed but challenging task. Numerous models were proposed to label various data and many approaches were designed…
Event-related potential (ERP), a specialized paradigm of electroencephalographic (EEG), reflects neurological responses to external stimuli or events, generally associated with the brain's processing of specific cognitive tasks. ERP plays a…
Personal assistant AI systems such as Siri, Cortana, and Alexa have become widely used as a means to accomplish tasks through natural language commands. However, components in these systems generally rely on supervised machine learning…
Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…
Echocardiography (echo) is the first imaging modality used when assessing cardiac function. The measurement of functional biomarkers from echo relies upon the segmentation of cardiac structures and deep learning models have been proposed to…
When a deep learning model is deployed in the wild, it can encounter test data drawn from distributions different from the training data distribution and suffer drop in performance. For safe deployment, it is essential to estimate the…
In class-incremental semantic segmentation, we have no access to the labeled data of previous tasks. Therefore, when incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previously learned…
Event-related potentials (ERP) are measurements of brain activity with wide applications in basic and clinical neuroscience, that are typically estimated using the average of many trials of electroencephalography signals (EEG) to…
As deep learning has achieved state-of-the-art performance for many tasks of EEG-based BCI, many efforts have been made in recent years trying to understand what have been learned by the models. This is commonly done by generating a heatmap…
Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a…
We exploit a self-supervised deep multi-task learning framework for electrocardiogram (ECG) -based emotion recognition. The proposed solution consists of two stages of learning a) learning ECG representations and b) learning to classify…
Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…
Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…
Self-training is a powerful approach to deep learning. The key process is to find a pseudo-label for modeling. However, previous self-training algorithms suffer from the over-confidence issue brought by the hard labels, even some…