Fangyun Wei

GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond

2019

The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, through a rigorous empirical analysis, we have found that the global contexts modeled …

Aligning Pretraining for Detection via Object-Level Contrastive Learning

2021 · arXiv (Cornell University)

Image-level contrastive representation learning has proven to be highly effective as a generic model for transfer learning. Such generality for transfer learning, however, sacrifices specificity if we are interested in a certain downstream task. We …