Although augmentations (eg, perturbation of graph edges, image crops) boost the efficiency
of Contrastive Learning (CL), feature level augmentation is another plausible …

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an
encoder which can be used as a general-purpose feature extractor, such that downstream …

Self-supervised learning allows AI systems to learn effective representations from large
amounts of data using tasks that do not require costly labeling. Mode collapse, ie, the model …

Learning effective visual representations without human supervision is a critical problem for
the task of semantic segmentation of remote sensing images (RSIs), where pixel-level …

Self-supervised learning models have been shown to learn rich visual representations
without requiring human annotations. However, in many real-world scenarios, labels are …

Supervised machine learning provides state-of-the-art solutions to a wide range of computer
vision problems. However, the need for copious labelled training data limits the capabilities …

For self-supervised contrastive learning, models can easily collapse and generate trivial
constant solutions. The issue has been mitigated by recent improvement on objective …

Given a union of non-linear manifolds, non-linear subspace clustering or manifold clustering
aims to cluster data points based on manifold structures and also learn to parameterize each …

Self-supervised contrastive learning is a powerful tool to learn visual representation without
labels. Prior work has primarily focused on evaluating the recognition accuracy of various …

Adversarial training (AT) for robust representation learning and self-supervised learning
(SSL) for unsupervised representation learning are two active research fields. Integrating AT …