University of Cambridge > Talks.cam > Cambridge Ellis Unit > Cambridge Ellis Unit Seminar Series- Dr Neil Houlsby- Learning general visual representations: data, scaling laws, and fewer convolutions

Cambridge Ellis Unit Seminar Series- Dr Neil Houlsby- Learning general visual representations: data, scaling laws, and fewer convolutions

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Kimberly Cole.

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.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.

This talk is part of the Cambridge Ellis Unit series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity