Abstract
Recent advances in deep learning have led to the development of accurate and efficient models for medical image segmentation. However, learning highly accurate models relies on the availability of large-scale annotated datasets. Due to this, model performance drops drastically when evaluated on label-scarce datasets having visually distinct images. Domain adaptation tries to mitigate this degradation. In this talk, I will present some of our recent works on domain adaptive medical image segmentation. In particular, source-free and fully test-time adaptive segmentation methods will be presented.
Speaker’s Bio
Vishal M. Patel is an Associate Professor in the Department of Electrical and Computer Engineering (ECE) at Johns Hopkins University. Prior to joining Hopkins, he was an A. Walter Tyson Assistant Professor in the Department of ECE at Rutgers University and a member of the research faculty at the University of Maryland Institute for Advanced Computer Studies (UMIACS). He completed his Ph.D. in Electrical Engineering from the University of Maryland, College Park, MD, in 2010. He has received a number of awards including the 2021 IEEE Signal Processing Society (SPS) Pierre-Simon Laplace Early Career Technical Achievement Award, the 2021 NSF CAREER Award, the 2021 IAPR Young Biometrics Investigator Award (YBIA), the 2016 ONR Young Investigator Award, the 2016 Jimmy Lin Award for Invention, A. Walter Tyson Assistant Professorship Award, Best Paper Awards at IEEE AVSS 2017 & 2019, IEEE BTAS 2015, IAPR ICB 2018, IEEE ICIP 2021, and two Best Student Paper Awards at IAPR ICPR 2018. He is an Associate Editor of the IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition Journal, and serves on the Machine Learning for Signal Processing (MLSP) Committee of the IEEE Signal Processing Society. He serves as the vice president of conferences for the IEEE Biometrics Council.