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
Proceedings Article
Label Inference Attacks Against Vertical Federated Learning
Chong Fu,Xuhong Zhang,Shouling Ji,Jinyin Chen,Jingzheng Wu,Shanqing Guo,Junfeng Zhou,Alex X. Liu,Ting Wang +8 more
TL;DR: The bottom model structure and the gradient update mechanism of VFL can be exploited by a malicious participant to gain the power to infer the privately owned labels and by abusing the bottom model, he/she can even infer labels beyond the training dataset.
Posted Content
Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning.
TL;DR: A simple technique to improve a generalization ability of deep RL agents by introducing a randomized (convolutional) neural network that randomly perturbs input observations, which enables trained agents to adapt to new domains by learning robust features invariant across varied and randomized environments.
Proceedings ArticleDOI
Semi-Supervised Action Recognition with Temporal Contrastive Learning
Ankit Singh,Omprakash Chakraborty,Ashutosh Varshney,Rameswar Panda,Rogerio Feris,Kate Saenko,Abir Das +6 more
TL;DR: In this paper, a two-pathway temporal contrastive model is proposed to maximize the similarity between encoded representations of the same video at two different speeds as well as minimize the similarity among different videos played at different speeds.
Proceedings ArticleDOI
Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
TL;DR: In this article, a data-uncertainty guided multi-phase learning method for semi-supervised object detection is proposed, which comprehensively considers divergent types of unlabeled images according to their difficulty levels, utilize them in different phases, and ensemble models from different phases together to generate ultimate results.
Proceedings ArticleDOI
SESS: Self-Ensembling Semi-Supervised 3D Object Detection
TL;DR: Zhang et al. as mentioned in this paper proposed a self-ensembling semi-supervised 3D object detection framework (SESS), which designs a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data.
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.