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
Journal ArticleDOI
Visualization, Discriminability and Applications of Interpretable Saak Features
TL;DR: The discriminant power of Saak features is demonstrated, and their classification performance in three well-known datasets (namely, MNIST, CIFAR-10 and STL-10) is shown by experimental results.
Posted Content
Virtual Adversarial Lipschitz Regularization
TL;DR: It is shown that using an explicit Lipschitz penalty is indeed viable and leads to state-of-the-art performance in terms of Inception Score and Fréchet Inception Distance when applied to Wasserstein GANs trained on CIFAR-10.
Journal ArticleDOI
Semi-supervised semantic segmentation network via learning consistency for remote sensing land-cover classification
TL;DR: A novel semantic segmentation neural network (S4Net) based on semi-supervised learning by using unlabeled data based on consistency regularization, which enforces the consistency of output under different random transforms and perturbations, such as random affine transform.
Journal ArticleDOI
A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
Jian Liang,Ran He,Tien-Ping Tan +2 more
TL;DR: Test-time adaptation (TTA) as discussed by the authors has the potential to adapt a pre-trained model to unlabeled data during testing, before making predictions, which is an emerging paradigm.
Posted Content
Privacy-Net: An Adversarial Approach for Identity-Obfuscated Segmentation of Medical Images.
TL;DR: In this paper, a client/server privacy-preserving network is proposed for multicentric medical image analysis, which is composed of an encoder network which removes identity-specific features from input medical images, a discriminator network that attempts to identify the subject from the encoded images, and a medical analysis network which analyzes the content of encoded images.
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.