相关论文: Hierarchical Text Classification Using Contrastive…

Graph contrastive learning (CL) methods learn node representations in a self-supervised manner by maximizing the similarity between the augmented node representations obtained via a GNN-based encoder. However, CL methods perform poorly on…

Contrastive vision-language models, such as CLIP, have garnered considerable attention for various downstream tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often…

Contrastive learning has achieved impressive success in generation tasks to militate the "exposure bias" problem and discriminatively exploit the different quality of references. Existing works mostly focus on contrastive learning on the…

The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual representation learning. However, existing research overlooks the…

Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document…

We investigate node representation learning on text-attributed graphs (TAGs), where nodes are associated with text information. Although recent studies on graph neural networks (GNNs) and pretrained language models (PLMs) have exhibited…

Class-Incremental Learning (CIL) enables models to learn new classes continually while preserving past knowledge. Recently, vision-language models like CLIP offer transferable features via multi-modal pre-training, making them well-suited…

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…

We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it…

Image enhancement is a significant research area in the fields of computer vision and image processing. In recent years, many learning-based methods for image enhancement have been developed, where the Look-up-table (LUT) has proven to be…

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for…

Multi-label image classification presents a challenging task in many domains, including computer vision and medical imaging. Recent advancements have introduced graph-based and transformer-based methods to improve performance and capture…

Contrastive learning has gained significant attention in short text clustering, yet it has an inherent drawback of mistakenly identifying samples from the same category as negatives and then separating them in the feature space (false…

A large amount of research on Convolutional Neural Networks has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as problems of hierarchical classification, in which the…

Contrastive learning (CL) has become a powerful approach for learning representations from unlabeled images. However, existing CL methods focus predominantly on visual appearance features while neglecting topological characteristics (e.g.,…

Inspired by the success of contrastive learning (CL) in computer vision and natural language processing, graph contrastive learning (GCL) has been developed to learn discriminative node representations on graph datasets. However, the…

Learning representations for individual instances when only bag-level labels are available is a fundamental challenge in multiple instance learning (MIL). Recent works have shown promising results using contrastive self-supervised learning…

This paper presents a CLIP-based unsupervised learning method for annotation-free multi-label image classification, including three stages: initialization, training, and inference. At the initialization stage, we take full advantage of the…

In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity…

In many real-world applications, the frequency distribution of class labels for training data can exhibit a long-tailed distribution, which challenges traditional approaches of training deep neural networks that require heavy amounts of…