Semi Supervised Representation Learning
Semi-supervised representation learning aims to leverage both labeled and unlabeled data to build robust and generalizable models, particularly valuable when labeled data is scarce. Current research focuses on improving model robustness to noisy or uncurated unlabeled data, exploring effective strategies for selecting representative labeled subsets, and developing novel architectures like contrastive learning and generative adversarial networks (GANs) to better integrate unlabeled information. These advancements are impacting diverse fields, including robotics, image classification, and medical imaging, by enabling more efficient and accurate model training with limited annotated datasets.
Papers
June 1, 2024
October 30, 2023
February 28, 2023
November 27, 2022
August 17, 2022
June 23, 2022
May 9, 2022