← Search

Jeffrey O. Zhang

2 accepted papers

2020

Side-Tuning: A Baseline for Network Adaptation via Additive Side Networks

ECCV 2020poster

When training a neural network for a desired task, one may prefer to adapt a pre-trained network rather than starting from randomly initialized weights. Adaptation can be useful in cases when training data is scarce, when a single learner needs to perform multiple tasks, or when one wishes to encode…

Cited by 257SourcePDFScholar
2019

Learning to Navigate Using Mid-Level Visual Priors

CoRL 2019

How much does having visual priors about the world (e.g. the fact that the world is 3D) assist in learning to perform downstream motor tasks (e.g. navigating a complex environment)? What are the consequences of not utilizing such visual priors in learning? We study these questions by integrating a g