Search Results for author:
Found 7 papers, 0 papers with code
ProtoVAE: Prototypical Networks for Unsupervised Disentanglement
Generative modeling and self-supervised learning have in recent years made great strides towards learning from data in a completely unsupervised way.
DOT-VAE: Disentangling One Factor at a Time
One promising approach to this endeavour is the problem of Disentanglement, which aims at learning the underlying generative latent factors, called the factors of variation, of the data and encoding them in disjoint latent representations.
FedNet2Net: Saving Communication and Computations in Federated Learning with Model Growing
Federated learning (FL) is a recently developed area of machine learning, in which the private data of a large number of distributed clients is used to develop a global model under the coordination of a central server without explicitly exposing the data.
Disentangling One Factor at a Time
While GANs have good performance, they suffer from difficulty in training and mode collapse, and while VAEs are stable to train, they do not perform as well as GANs in terms of interpretability.
Class-Similarity Based Label Smoothing for Confidence Calibration
The output of a neural network is a probability distribution where the scores are estimated confidences of the input belonging to the corresponding classes, and hence they represent a complete estimate of the output likelihood relative to all classes.
Feature Prioritization and Regularization Improve Standard Accuracy and Adversarial Robustness
We propose a model that employs feature prioritization by a nonlinear attention module and $L_2$ feature regularization to improve the adversarial robustness and the standard accuracy relative to adversarial training.
From Maxout to Channel-Out: Encoding Information on Sparse Pathways
Motivated by an important insight from neural science, we propose a new framework for understanding the success of the recently proposed "maxout" networks.
