Computer Vision researchers at Facebook are inventing new ways for computers to gain a higher level of understanding cued from the visual world around us.
We are creating visual sensors derived from digital images and videos that extract information about our environment, to further enable Facebook services to automate tasks that people automatically do today visually. Our ultimate goal is to automatically and intelligently enhance people’s experiences across Facebook products.
June 07, 2019
We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that state-of-the-art VQA models are notoriously brittle to linguistic variations in questions.
June 07, 2019
May 06, 2019
In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost.
Arslan Chaudhry, Marc'Aurelio Ranzato, Marcus Rohrbach, Mohamed Elhoseiny
May 06, 2019
May 06, 2019
In this paper we look at a scenario with fixed model capacity, and postulate that the learning process should not be selfish, i.e. it should account for future tasks to be added and thus leave enough capacity for them.
Rahaf Aljundi, Marcus Rohrbach, Tinne Tuytelaars
May 06, 2019