4 datasets found

The dataset used in the paper is a set of functions that are approximated using deep networks.

The proposed model consists of three components: 1) Coordinate base computation: uses a 2D coordinate grid as input and generates the bases, 2) Image feature computation:...

Deep networks for image classification often rely more on texture information than object shape. This paper presents a deep-learning model inspired by geometric moments, a...

Mixup is a widely adopted strategy for training deep networks, where additional samples are augmented by interpolating inputs and labels of training pairs. Mixup has shown to...