Seminar: Towards robust and efficient channel-adaptive models for multi-channel imaging

Dr. Plummer will discuss training channel-adaptive model; how we can take advantage of self-supervised techniques; how we can mitigate the effect of label noise, especially in the high levels of noise often seen in scientific data sets & when domain shifts that already exist in the training dataset make it challenging to identify noisy samples; the significant energy and storage requirements of training machine learning models, & the increasing need for resource-efficient methods.