The program will be available shortly. Please check back later.
Presented by Aiden Durrant, Assistant Professor at University of Aberdeen
Self-Supervised learning has revolutionised the way we perform large scale training. However, it is built on primitives of invariance to perturbations and transformations to learn key features. If we wish to move towards generalised visual world models, it is essential that properties of transformation to objects are preserved.
In this talk, we will discuss the motivation and potential application of equivariant self-supervised learning, and explore recent work employing architectural changes to introduce useful inductive biases.
In compliance with GDPR consent requirements, presentations given in a Visual Intelligence context may be recorded with the consent of the speaker. All recordings are edited to remove all faces, names and voices of other participants. Questions and comments by the audience will hence be removed and will not appear in the recording. With the freely given consent from the speaker, recorded presentation may be posted on the Visual Intelligence YouTube channel.
This seminar is open for members of the consortium. If you want to participate as a guest please sign up.
Aiden Durrant, Assistant Professor, University of Aberdeen
This seminar is open for members of the consortium. If you want to participate as a guest please sign up.
Aiden Durrant, Assistant Professor, University of Aberdeen
This seminar is open for members of the consortium. If you want to participate as a guest please sign up.