Cohere For AI - Guest Speaker: Shashanka Venkataramanan, PhD at INRIA

About the session: Self-supervised learning has unlocked the potential of scaling up pretraining to billions of images, since annotation is unnecessary. But are we making the best use of data? How more economical can we be? In this work, we attempt to answer this question by making two contributions. First, we investigate first-person videos and introduce a "Walking Tours" dataset. These videos are high-resolution, hours-long, captured in a single uninterrupted take, depicting a large number of objects and actions with natural scene transitions. They are unlabeled and uncurated, thus realistic for self-supervision and comparable with human learning.Second, we introduce a novel self-supervised image pretraining method tailored for learning from continuous videos. Existing methods typically adapt image-based pretraining approaches to incorporate more frames. Instead, we advocate a "tracking to learn to recognize" approach. Our method called DoRA, leads to attention maps that Discover and tRAck objects over time in an end-to-end manner, using transformer cross-attention. We derive multiple views from the tracks and use them in a classical self-supervised distillation loss. Using our novel approach, a single Walking Tours video remarkably becomes a strong competitor to ImageNet for several image and video downstream tasks.

About the speaker: Shashanka Venkataramanan is a final year doctoral student with the LinkMedia team at INRIA, where he is advised by Dr. Yannis Avrithis, Dr. Ewa Kijak and Dr. Laurent Amsaleg. His work mainly focuses on developing algorithms to enhance instance and category-level visual representations in the supervised and self-supervised settings.

Add event to calendar

Apple Google Office 365 Outlook Outlook.com Yahoo