Research Area
Computer Vision
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.
Latest Publications
Cycle-Consistency for Robust Visual Question Answering
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.
Efficient Lifelong Learning with A-GEM
In this work, we investigate the efficiency of current lifelong approaches, in terms of sample complexity, computational and memory cost.
Selfless Sequential Learning
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.
Facebook © 2020