Related papers: Supervised Adversarial Contrastive Learning for Em…

Electroencephalography-to-Text generation (EEG-to-Text), which aims to directly generate natural text from EEG signals has drawn increasing attention in recent years due to the enormous potential for Brain-computer interfaces (BCIs).…

We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have shown impressive…

Semi-supervised learning for medical image segmentation is an important area of research for alleviating the huge cost associated with the construction of reliable large-scale annotations in the medical domain. Recent semi-supervised…

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…

Self-supervised Contrastive Learning (CL) has been recently shown to be very effective in preventing deep networks from overfitting noisy labels. Despite its empirical success, the theoretical understanding of the effect of contrastive…

Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation…

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with more diverse distributions and train extra components such as…

Despite profound successes, contrastive representation learning relies on carefully designed data augmentations using domain specific knowledge. This challenge is magnified in natural language processing where no general rules exist for…

Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents…

In real life, adversarial attack to deep learning models is a fatal security issue. However, the issue has been rarely discussed in a widely used class-incremental continual learning (CICL). In this paper, we address problems of applying…

Contrastive self-supervised learning (CSL) is an approach to learn useful representations by solving a pretext task that selects and compares anchor, negative and positive (APN) features from an unlabeled dataset. We present a conceptual…

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on ASC. A CL…

We explore the value of weak labels in learning transferable representations for medical images. Compared to hand-labeled datasets, weak or inexact labels can be acquired in large quantities at significantly lower cost and can provide…

Knowledge tracing and dropout prediction are crucial for online education to estimate students' knowledge states or to prevent dropout rates. While traditional systems interacting with students suffered from data sparsity and overfitting,…

Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach…

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…

Although there is significant progress in supervised semantic segmentation, it remains challenging to deploy the segmentation models to unseen domains due to domain biases. Domain adaptation can help in this regard by transferring knowledge…

The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple connections for cross-modal fusion and ignored the…

Existed pre-trained models have achieved state-of-the-art performance on various text classification tasks. These models have proven to be useful in learning universal language representations. However, the semantic discrepancy between…

In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution…