Related papers: Contrastive Learning and Cycle Consistency-based T…

Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive transformer network (ADAPTER), a simple but effective solution…

Deep learning-based diagnostic models often suffer performance drops due to distribution shifts between training (source) and test (target) domains. Collecting and labeling sufficient target domain data for model retraining represents an…

Multi-Task Learning (MTL) is a framework, where multiple related tasks are learned jointly and benefit from a shared representation space, or parameter transfer. To provide sufficient learning support, modern MTL uses annotated data with…

Graphs model complex relationships between entities, with nodes and edges capturing intricate connections. Node representation learning involves transforming nodes into low-dimensional embeddings. These embeddings are typically used as…

We propose a novel approach to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans and the other way around. Solving this task has two important applications: (i) to automatically generate contrast CT scans…

Real-world application models are commonly deployed in dynamic environments, where the target domain distribution undergoes temporal changes. Continual Test-Time Adaptation (CTTA) has recently emerged as a promising technique to gradually…

We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM…

Aspect Sentiment Triplet Extraction (ASTE) has achieved promising results while relying on sufficient annotation data in a specific domain. However, it is infeasible to annotate data for each individual domain. We propose to explore ASTE in…

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…

Current sign language translation (SLT) approaches often rely on gloss-based supervision with Connectionist Temporal Classification (CTC), limiting their ability to handle non-monotonic alignments between sign language video and spoken…

Graph Neural Networks (GNNs) have achieved remarkable success in learning node representations and have shown strong performance in tasks such as node classification. However, recent findings indicate that the presence of noise in…

Recently, deep end-to-end learning has been studied for intent classification in Spoken Language Understanding (SLU). However, end-to-end models require a large amount of speech data with intent labels, and highly optimized models are…

Detecting trajectory anomalies is a vital task in modern Intelligent Transportation Systems (ITS), enabling the identification of unsafe, inefficient, or irregular travel behaviours. While deep learning has emerged as the dominant approach,…

Contrastive learning with Transformer-based sequence encoder has gained predominance for sequential recommendation. It maximizes the agreements between paired sequence augmentations that share similar semantics. However, existing…

Connectionist Temporal Classification (CTC) is a widely used approach for automatic speech recognition (ASR) that performs conditionally independent monotonic alignment. However for translation, CTC exhibits clear limitations due to the…

Existing 3D object detection suffers from expensive annotation costs and poor transferability to unknown data due to the domain gap, Unsupervised Domain Adaptation (UDA) aims to generalize detection models trained in labeled source domains…

Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing methods rely on binary contrastive objectives that overlook the…

For low-semantic sensor signals from human activity recognition (HAR), contrastive learning (CL) is essential to implement novel applications or generic models without manual annotation, which is a high-performance self-supervised learning…

Multi-task learning (MTL) is an active field in deep learning in which we train a model to jointly learn multiple tasks by exploiting relationships between the tasks. It has been shown that MTL helps the model share the learned features…

Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…