Related papers: A Theoretical Analysis of Contrastive Unsupervised…

Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this…

Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one of the leading learning paradigms in the absence of labels…

Deep learning-based recommender systems have achieved remarkable success in recent years. However, these methods usually heavily rely on labeled data (i.e., user-item interactions), suffering from problems such as data sparsity and…

Contrastive learning is a highly effective method for learning representations from unlabeled data. Recent works show that contrastive representations can transfer across domains, leading to simple state-of-the-art algorithms for…

Unsupervised learning is just at a tipping point where it could really take off. Among these approaches, contrastive learning has seen tremendous progress and led to state-of-the-art performance. In this paper, we construct a novel…

Self-supervised pretraining on unlabeled data followed by supervised fine-tuning on labeled data is a popular paradigm for learning from limited labeled examples. We extend this paradigm to the classical positive unlabeled (PU) setting,…

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential treatments. Early works…

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…

Unsupervised contrastive learning has gained increasing attention in the latest research and has proven to be a powerful method for learning representations from unlabeled data. However, little theoretical analysis was known for this…

Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…

Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks. In this paper, we present a hierarchical multi-label…

Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems such as multi-domain or multi-attribute transfer. The vast majority of such works leverages the strengths of adversarial…

A lot of recent advances in unsupervised feature learning are based on designing features which are invariant under semantic data augmentations. A common way to do this is contrastive learning, which uses positive and negative samples. Some…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled…

Though language model text embeddings have revolutionized NLP research, their ability to capture high-level semantic information, such as relations between entities in text, is limited. In this paper, we propose a novel contrastive learning…

Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these…

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…