Adversarial Ladder Networks
نویسندگان
چکیده
The use of unsupervised data in addition to supervised data has lead to a significant improvement when training discriminative neural networks. However, the best results were achieved with a training process that is divided in two parts: first an unsupervised pre-training step is done for initializing the weights of the network and after these weights are refined with the use of supervised data. Recently, a new neural network topology called Ladder Network, where the key idea is based in some properties of hierarchichal latent variable models, has been proposed as a technique to train a neural network using supervised and unsupervised data at the same time with what is called semi-supervised learning. This technique has reached state of the art classification. On the other hand adversarial noise has improved the results of classical supervised learning. In this work we add adversarial noise to the ladder network and get state of the art classification, with several important conclusions on how adversarial noise can help in addition with new possible lines of investigation. We also propose an alternative to add adversarial noise to unsupervised data.
منابع مشابه
Virtual Adversarial Ladder Networks For Semi-supervised Learning
Semi-supervised learning (SSL) partially circumvents the high cost of labelling data by augmenting a small labeled dataset with a large and relatively cheap unlabeled dataset drawn from the same distribution. This paper offers a novel interpretation of two deep learning-based SSL approaches, ladder networks and virtual adversarial training (VAT), as applying distributional smoothing to their re...
متن کاملImprovement of generative adversarial networks for automatic text-to-image generation
This research is related to the use of deep learning tools and image processing technology in the automatic generation of images from text. Previous researches have used one sentence to produce images. In this research, a memory-based hierarchical model is presented that uses three different descriptions that are presented in the form of sentences to produce and improve the image. The proposed ...
متن کاملClose-to-clean Regularization Relates Virtual Adversarial Training, Ladder Networks and Others
We propose a regularization framework where we feed an original clean data point and a nearby point through a mapping, which is then penalized by the Euclidian distance between the corresponding outputs. The nearby point may be chosen randomly or adversarially. We relate this framework to many existing regularization methods: It is a stochastic estimate of penalizing the Frobenius norm of the J...
متن کاملUnderstanding Regularization by Virtual Adversarial Training, Ladder Networks and Others
We study a regularization framework where we feed an original clean data point and a nearby point through a mapping, which is then penalized by the Euclidian distance between the corresponding outputs. The nearby point may be chosen randomly or adversarially. A more general form of this framework has been presented in (Bachman et al., 2014). We relate this framework to many existing regularizat...
متن کاملAutomatic Colorization of Grayscale Images Using Generative Adversarial Networks
Automatic colorization of gray scale images poses a unique challenge in Information Retrieval. The goal of this field is to colorize images which have lost some color channels (such as the RGB channels or the AB channels in the LAB color space) while only having the brightness channel available, which is usually the case in a vast array of old photos and portraits. Having the ability to coloriz...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1611.02320 شماره
صفحات -
تاریخ انتشار 2016