Mahsa Baktashmotlagh

Dr. Mahsa Baktashmotlagh is a leading researcher in the field of machine learning, with a focus on domain adaptation, generalization, and robustness of models across different data distributions. Her work has significantly contributed to the development of techniques that enable models to perform well in unseen environments, which is crucial for real-world applications where data distributions can vary widely. She is known for her innovative approaches to domain generalization, including methods that leverage gradient signal-to-noise ratios, pseudo-labeling strategies, and knowledge distillation. Dr. Baktashmotlagh has also made notable contributions to computer vision, particularly in the areas of 3D object detection and active learning. Her research has been widely published in top-tier conferences such as NeurIPS, ICCV, ICLR, and CVPR, and she has received numerous awards for her work. She is currently affiliated with the University of Melbourne, where she leads research initiatives in machine learning and computer vision.

Mahsa Baktashmotlagh is a researcher at the University of Queensland with expertise in Machine Learning and Computer Vision. Her work focuses on domain adaptation, domain generalization, and robustness in machine learning models. She has published extensively on topics such as unsupervised domain adaptation, adversarial domain adaptation, and deep domain generalization. Her research explores methods to improve model performance across different domains by leveraging invariant representations and distribution matching. Additionally, she has contributed to applications in 3D shape inference, image translation, and network intrusion detection. Her work emphasizes the development of robust and generalizable models for real-world scenarios.