Self Supervised
Self-supervised learning (SSL) aims to train machine learning models using unlabeled data by designing pretext tasks that encourage the model to learn useful representations. Current research focuses on improving generalization, mitigating overfitting, and developing efficient architectures like transformers and CNNs for various modalities (images, audio, point clouds, fMRI data). SSL's significance lies in its ability to leverage vast amounts of readily available unlabeled data, leading to improved performance on downstream tasks and reducing the reliance on expensive and time-consuming manual labeling, particularly impacting fields like medical imaging, speech processing, and autonomous driving.
Papers
Shot Noise Reduction in Radiographic and Tomographic Multi-Channel Imaging with Self-Supervised Deep Learning
Yaroslav Zharov, Evelina Ametova, Rebecca Spiecker, Tilo Baumbach, Genoveva Burca, Vincent Heuveline
Supervised Masked Knowledge Distillation for Few-Shot Transformers
Han Lin, Guangxing Han, Jiawei Ma, Shiyuan Huang, Xudong Lin, Shih-Fu Chang