Related papers: Speech SIMCLR: Combining Contrastive and Reconstru…

In this study, we present a simple multi-channel framework for contrastive learning (MC-SimCLR) to encode 'what' and 'where' of spatial audios. MC-SimCLR learns joint spectral and spatial representations from unlabeled spatial audios,…

Session-based recommendation, which aims to predict the next item of users' interest as per an existing sequence interaction of items, has attracted growing applications of Contrastive Learning (CL) with improved user and item…

Self-supervised contrastive learning (CL) has achieved state-of-the-art performance in representation learning by minimizing the distance between positive pairs while maximizing that of negative ones. Recently, it has been verified that the…

Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual…

Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to boost the performance of various application tasks. These pretraining methods are frequently extended with…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…

Though offering amazing contextualized token-level representations, current pre-trained language models actually take less attention on acquiring sentence-level representation during its self-supervised pre-training. If self-supervised…

Recent work has shown that self-supervised pre-training leads to improvements over supervised learning on challenging visual recognition tasks. CLIP, an exciting new approach to learning with language supervision, demonstrates promising…

Contrastive self-supervised learning (CSL) for speaker verification (SV) has drawn increasing interest recently due to its ability to exploit unlabeled data. Performing data augmentation on raw waveforms, such as adding noise or…

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or…

In Computer Vision, self-supervised contrastive learning enforces similar representations between different views of the same image. The pre-training is most often performed on image classification datasets, like ImageNet, where images…

In Self-Supervised Learning (SSL), various pretext tasks are designed for learning feature representations through contrastive loss. However, previous studies have shown that this loss is less tolerant to semantically similar samples due to…

The objective of this paper is visual-only self-supervised video representation learning. We make the following contributions: (i) we investigate the benefit of adding semantic-class positives to instance-based Info Noise Contrastive…

Speech representation learning plays a vital role in speech processing. Among them, self-supervised learning (SSL) has become an important research direction. It has been shown that an SSL pretraining model can achieve excellent performance…

Self-supervised visual representation learning aims to learn useful representations without relying on human annotations. Joint embedding approach bases on maximizing the agreement between embedding vectors from different views of the same…

Sign language recognition (SLR) is a machine learning task aiming to identify signs in videos. Due to the scarcity of annotated data, unsupervised methods like contrastive learning have become promising in this field. They learn meaningful…

Recent breakthroughs in the field of semi-supervised learning have achieved results that match state-of-the-art traditional supervised learning methods. Most successful semi-supervised learning approaches in computer vision focus on…

In this paper, we study contrastive learning from an optimization perspective, aiming to analyze and address a fundamental issue of existing contrastive learning methods that either rely on a large batch size or a large dictionary of…

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear what characteristics of their representations lead to high downstream accuracies. In this work, we characterize properties that SSL representations…

Unsupervised learning has been a long-standing goal of machine learning and is especially important for medical image analysis, where the learning can compensate for the scarcity of labeled datasets. A promising subclass of unsupervised…