The Cambridge ELLIS Unit has started a Seminar Series that will include talks by leading researchers in the area of machine learning and AI. Our next speaker will be Dr. Neil Houlsby. Details of his talk can be found below.
Please note that we require all attendees to have valid Zoom accounts to join.
Title: “Learning general visual representations: data, scaling laws, and fewer convolutions”
Abstract: Learning general visual representations, those useful for many tasks, is a key challenge in Computer Vision. For many years, Convolution Neural Networks (CNNs), typically trained on the ImageNet dataset, have been used as a “backbone”, or starting point, for downstream tasks. Perhaps surprisingly, recent work has demonstrated large CNNs transfer well to small downstream tasks, even in the few-shot regime. However, such CNNs need large datasets for pre-training. While CNNs appear to have just the right inductive biases for small or medium-scale training, are they still optimal in modern transfer learning regimes? In this talk we will discuss some recent trends, and surprising findings, in architecture design, scaling laws, and visual representation learning.