Unsupervised Learning
Unsupervised learning aims to extract meaningful patterns and structures from unlabeled data, addressing the limitations of supervised methods that require extensive labeled datasets. Current research focuses on developing robust algorithms and model architectures, such as autoencoders, generative models (like Gaussian Mixture Models), and contrastive learning approaches, to improve clustering, anomaly detection, and representation learning. These advancements are impacting diverse fields, including medical image analysis, financial market prediction, and signal processing, by enabling efficient analysis of large, unlabeled datasets and reducing reliance on expensive manual labeling.
Papers
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
James Oldfield, Christos Tzelepis, Yannis Panagakis, Mihalis A. Nicolaou, Ioannis Patras
From Keypoints to Object Landmarks via Self-Training Correspondence: A novel approach to Unsupervised Landmark Discovery
Dimitrios Mallis, Enrique Sanchez, Matt Bell, Georgios Tzimiropoulos