Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
Reads0
Chats0
TLDR
Virtual adversarial training (VAT) as discussed by the authors is a regularization method based on virtual adversarial loss, which is a measure of local smoothness of the conditional label distribution given input.Abstract:
We propose a new regularization method based on virtual adversarial loss: a new measure of local smoothness of the conditional label distribution given input. Virtual adversarial loss is defined as the robustness of the conditional label distribution around each input data point against local perturbation. Unlike adversarial training, our method defines the adversarial direction without label information and is hence applicable to semi-supervised learning. Because the directions in which we smooth the model are only “virtually” adversarial, we call our method virtual adversarial training (VAT). The computational cost of VAT is relatively low. For neural networks, the approximated gradient of virtual adversarial loss can be computed with no more than two pairs of forward- and back-propagations. In our experiments, we applied VAT to supervised and semi-supervised learning tasks on multiple benchmark datasets. With a simple enhancement of the algorithm based on the entropy minimization principle, our VAT achieves state-of-the-art performance for semi-supervised learning tasks on SVHN and CIFAR-10.read more
Citations
More filters
Posted Content
Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering.
Lars Schmarje,Johannes Brünger,Monty Santarossa,Simon-Martin Schröder,Rainer Kiko,Reinhard Koch +5 more
TL;DR: This work proposes a novel framework for handling semi-supervised classifications of fuzzy labels based on the idea of overclustering to detect substructures in these fuzzy labels, and shows on the common image classification dataset STL-10 that it is faster and has better overclUSTering performance than previous work.
Posted Content
Learning to Detect Important People in Unlabelled Images for Semi-supervised Important People Detection
TL;DR: This work iteratively learns to assign pseudo-labels to individuals in un-annotated images and learns to update the important people detection model based on data with both labels and pseudo-label estimation, and introduces a ranking strategy for pseudo- label estimation.
Posted Content
Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks
TL;DR: The proposed method simultaneously estimates the target distribution and the quality of each data which is defined as the correlation between the target and data generating distributions, a Cholesky Block that enables modeling dependencies among mixture distributions in a differentiable manner.
Posted Content
Uncertainty-Aware Deep Calibrated Salient Object Detection.
TL;DR: An uncertaintyaware deep SOD network is introduced, and two strategies from different perspectives to preventDeep SOD networks from being overconfident are proposed, and a new saliency evaluation metric is proposed to measure how the model is calibrated on a given dataset.
Journal ArticleDOI
A Framework for Distributed Semi-supervised Learning Using Single-layer Feedforward Networks
Jin Xie,San Yang Liu,Jia-Xi Chen +2 more
TL;DR: In this article , the authors proposed a framework for manifold regularization based distributed semi-supervised learning (DSSL) using single layer feed-forward neural network (SLFNN).
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Generative Adversarial Nets
Ian Goodfellow,Jean Pouget-Abadie,Mehdi Mirza,Bing Xu,David Warde-Farley,Sherjil Ozair,Aaron Courville,Yoshua Bengio +7 more
TL;DR: A new framework for estimating generative models via an adversarial process, in which two models are simultaneously train: a generative model G that captures the data distribution and a discriminative model D that estimates the probability that a sample came from the training data rather than G.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.