Research
My research interests span a wide range of topics related to computer vision and statistical learning. That said, I enjoy both theoretical work and practical applications. Currently, in pursuit of a closed-form solution to solve abstract reasoning. The ultimate goal is to build conscious systems that evolve and learn with time as we humans do. Representative publications are highlighted.
|
|
Doctor of Crosswise: Reducing Over-parametrization in Neural Networks.
Curtò,
Zarzà,
Kitani,
King and
Lyu.
code
Dr. of Crosswise proposes a new architecture to reduce over-parametrization in Neural Networks. It introduces an operand for rapid computation in the framework of Deep Learning that leverages learned weights.
|
|
High-resolution Deep Convolutional Generative Adversarial Networks.
Curtò,
Zarzà,
Torre,
King and
Lyu.
dataset /
supplement /
video
In order to boost network convergence of DCGAN and achieve good-looking high-resolution results we propose a new layered network, HDCGAN, that incorporates current state-of-the-art techniques for this effect.
Recognitions:
State-of-the-art in synthetic image generation on CelebA 128x128 (MS-SSIM). 2017.
State-of-the-art in synthetic image generation on CelebA 64x64 (FID). 2017.
|
|
Segmentation of Objects by Hashing.
Curtò,
Zarzà,
Smola and
Gool.
We propose a novel approach to address the problem of Simultaneous Detection and Segmentation. We use an efficient and accurate procedure that exploits the feature information of the hierarchy using Locality Sensitive Hashing.
|
|
McKernel: A Library for Approximate Kernel Expansions in Log-linear Time.
Curtò,
Zarzà,
Yang,
Smola,
Torre,
Ngo and
Gool.
code /
slides /
coverage
McKernel introduces a framework to use kernel approximates in the mini-batch setting with Stochastic Gradient
Descent (SGD) as an alternative to Deep Learning.
|
|