Evan Shelhamer

Evan Shelhamer is an Assistant Professor at the University of British Columbia (UBC), a member of the Vector Institute, and holds a Canada CIFAR AI Chair. He earned his PhD in Computer Science from UC Berkeley in 2019, advised by Trevor Darrell as part of the Berkeley Artificial Intelligence Research (BAIR) Lab. Previously, he completed dual degrees in Computer Science (Artificial Intelligence) and Psychology at the University of Massachusetts Amherst, advised by Erik Learned-Miller. Before academia, he worked as a research scientist at Adobe (visiting MIT) and Google DeepMind (London/San Francisco).

His research focuses on machine learning and computer vision, emphasizing test-time adaptation, adversarial robustness, and remote sensing applications. Notable contributions include the Caffe framework (ACM MM 2024 Test-of-Time Award), Fully Convolutional Networks (CVPR 2025 Test-of-Time Award), and Tent for test-time adaptation. He actively organizes workshops on test-time adaptation, continual learning, and remote sensing at major conferences.

Shelhamer serves as an Area Chair for CVPR, NeurIPS, ICLR, and ICCV, and is an Action Editor for TMLR. His work bridges foundational research with practical tools, emphasizing open science and efficient algorithms.