Related papers: Fast and Featureless Node Representation Learning …

Pre-training representations (a.k.a. foundation models) has recently become a prevalent learning paradigm, where one first pre-trains a representation using large-scale unlabeled data, and then learns simple predictors on top of the…

Self-training methods have proven to be effective in exploiting abundant unlabeled data in semi-supervised learning, particularly when labeled data is scarce. While many of these approaches rely on a cross-entropy loss function (CE), recent…

Contrastive learning underpins most current self-supervised time series representation methods. The strategy for constructing positive and negative sample pairs significantly affects the final representation quality. However, due to the…

Many Click-Through Rate (CTR) prediction works focused on designing advanced architectures to model complex feature interactions but neglected the importance of feature representation learning, e.g., adopting a plain embedding layer for…

This paper presents a simple yet effective two-stage framework for semi-supervised medical image segmentation. Unlike prior state-of-the-art semi-supervised segmentation methods that predominantly rely on pseudo supervision directly on…

Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our objective is to learn representations that are invariant to…

Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations that are not…

Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and…

In this paper we present a world model, which learns causal features using the invariance principle. In particular, we use contrastive unsupervised learning to learn the invariant causal features, which enforces invariance across…

Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable…

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches…

Unsupervised learning methods for feature extraction are becoming more and more popular. We combine the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to…

Contrastive learning has shown promising potential for learning robust representations by utilizing unlabeled data. However, constructing effective positive-negative pairs for contrastive learning on facial behavior datasets remains…

Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…

Recently, contrastiveness-based augmentation surges a new climax in the computer vision domain, where some operations, including rotation, crop, and flip, combined with dedicated algorithms, dramatically increase the model generalization…

Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views of unlabeled samples and then learns effective…

Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations. The idea is to make features of transformed versions of the same images similar…

The recent success of SimCSE has greatly advanced state-of-the-art sentence representations. However, the original formulation of SimCSE does not fully exploit the potential of hard negative samples in contrastive learning. This study…

A fundamental challenge of bipartite graph representation learning is how to extract informative node embeddings. Self-Supervised Learning (SSL) is a promising paradigm to address this challenge. Most recent bipartite graph SSL methods are…