Domain Shift Problem
The domain shift problem arises when machine learning models trained on one data distribution (source domain) perform poorly on data from a different distribution (target domain). Current research focuses on mitigating this issue through techniques like test-time adaptation (TTA), which adjusts models to target domains using unlabeled data, and domain generalization (DG), which aims to build models robust across unseen domains. These efforts leverage various approaches, including diffusion models, contrastive learning, and adversarial training, with applications spanning diverse fields such as medical image analysis, autonomous driving, and speech recognition, ultimately improving the reliability and generalizability of AI systems.
Papers
September 26, 2024
August 11, 2024
April 12, 2024
March 22, 2024
February 7, 2024
January 26, 2024
December 22, 2023
December 8, 2023
November 27, 2023
August 19, 2023
July 24, 2023
May 31, 2023
April 25, 2023
March 10, 2023
March 9, 2023
February 3, 2023
December 31, 2022
December 3, 2022
November 30, 2022