Бібліографічний опис:
Kilianovskyi Mykhailo. Split Activation Networks for Neural Fields. Ukrainian Catholic University, Faculty of Applied Sciences, Department of Computer Sciences. Lviv 2023, 49 p.
Короткий опис (реферат):
Neural field modeling is a developing area that improves state-of-the-art results in
tasks such as 3D scene reconstruction, image manipulation, generative modeling,
and other aspects of deep learning. In this work, we present SplitNet, a novel neural network architecture for neural field modeling that combines multiple activation
functions in a single layer. We try different techniques to improve performance,
such as proper weight initialization, and benchmark its performance on image representation, 3D scene reconstruction, and image classification tasks. As a part of the
work, we found a way to improve the performance of previous work on implicit
neural networks with sinusoidal activations in a limited setting and study how well
this improvement generalizes to other tasks and data.