Related papers: miCSE: Mutual Information Contrastive Learning for…

Multiview network embedding aims at projecting nodes in the network to low-dimensional vectors, while preserving their multiple relations and attribute information. Contrastive learning approaches have shown promising performance in this…

Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting…

Recent unsupervised contrastive representation learning follows a Single Instance Multi-view (SIM) paradigm where positive pairs are usually constructed with intra-image data augmentation. In this paper, we propose an effective approach…

Contrastive learning has emerged as a prominent branch of self-supervised learning for several years. Especially, CLIP, which applies contrastive learning to large sets of captioned images, has garnered significant attention. Recently,…

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

The prompt has become an effective linguistic tool for utilizing pre-trained language models. However, in few-shot scenarios, subtle changes in the prompt design always make the result widely different, and the prompt learning methods also…

BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…

Correlation exploitation is essential for efficient multi-user channel estimation (MUCE) in massive MIMO systems. However, the existing works either rely on presumed strong correlation or learn the correlation through large amount of…

Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a…

Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieved state-of-the-art performance. However, existing solutions heavily rely on the exploitation of lexical features and their distributional…

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…

Few-shot learning has emerged as a powerful paradigm for training models with limited labeled data, addressing challenges in scenarios where large-scale annotation is impractical. While extensive research has been conducted in the image…

To extract robust deep representations from long sequential modeling of speech data, we propose a self-supervised learning approach, namely Contrastive Separative Coding (CSC). Our key finding is to learn such representations by separating…

Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality…

In this paper, we explore how to utilize pre-trained language model to perform few-shot text classification where only a few annotated examples are given for each class. Since using traditional cross-entropy loss to fine-tune language model…

In-Batch contrastive learning is a state-of-the-art self-supervised method that brings semantically-similar instances close while pushing dissimilar instances apart within a mini-batch. Its key to success is the negative sharing strategy,…

While humans can solve a visual puzzle that requires logical reasoning by observing only few samples, it would require training over large amount of data for state-of-the-art deep reasoning models to obtain similar performance on the same…

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

Multilingual information retrieval (IR) is challenging since annotated training data is costly to obtain in many languages. We present an effective method to train multilingual IR systems when only English IR training data and some parallel…

Multi-view representation learning has developed rapidly over the past decades and has been applied in many fields. However, most previous works assumed that each view is complete and aligned. This leads to an inevitable deterioration in…