research
∙
08/18/2020
Training Deep Neural Networks Without Batch Normalization
Training neural networks is an optimization problem, and finding a decen...
share
research
∙
03/26/2020
P ≈ NP, at least in Visual Question Answering
In recent years, progress in the Visual Question Answering (VQA) field h...
research
∙
03/22/2018
What do Deep Networks Like to See?
We propose a novel way to measure and understand convolutional neural ne...
research
∙
03/21/2018
Adversarial Defense based on Structure-to-Signal Autoencoders
Adversarial attack methods have demonstrated the fragility of deep neura...
research
∙
09/18/2017
Multi-Task Learning for Segmentation of Building Footprints with Deep Neural Networks
The increased availability of high resolution satellite imagery allows t...
research
∙
07/25/2016