Simone Marullo (University of Siena)
When: Oct 20th, 2021 – 11:00 – 11:45 AM
Where: Google meet link
Description
Designing agents that autonomously learn in a visual environment is not that easy, since standard supervised offline strategies are not available. We want to discuss novel techniques, exploiting a human-like attention mechanism both for learning and for interaction. We devise a simple unsupervised loss function based on spatio-temporal coherence. We show experimental validation that highlights weaknesses of standard large models.
19 October 2021
| Category: Seminars