A seminar of the A3SI team of the LIGM (joint research unit of Paris Est University) will take place on Tuesday, May 29 at 15:30, in the meeting room B 412 of the IMAGINE group (ENPC - Bat Coriolis).
Abstract: Computer vision has made impressive gains through the use of deep learning models, trained with large-scale tagged data. However, labels require expertise and curation and are expensive to collect. Even worse, direct semantic supervision often leads the learning algorithms "cheating" and taking shortcuts, instead of actually doing the work. In this talk, I will briefly summarize several of my group's efforts to combat this using self-supervision, meta-supervision, and curiosity — all ways of using the data as its own supervision. These lead to practical applications in image synthesis, image forensics, audio-visual source separation, etc.