Semi-supervised Learning using Adversarial Training with Good and Bad Samples
In this work, we investigate semi-supervised learning (SSL) for image classification using adversarial training. Previous results have illustrated that generative adversarial networks (GANs) can be used for multiple purposes. Triple-GAN, which aims to jointly optimize model components by incorporating three players, generates suitable image-label pairs to compensate for the lack of labeled data in SSL with improved benchmark performance. Conversely, Bad (or complementary) GAN, optimizes generation to produce complementary data-label pairs and force a classifier's decision boundary to lie between data manifolds. Although it generally outperforms Triple-GAN, Bad GAN is highly sensitive to the amount of labeled data used for training. Unifying these two approaches, we present unified-GAN (UGAN), a novel framework that enables a classifier to simultaneously learn from both good and bad samples through adversarial training. We perform extensive experiments on various datasets and demonstrate that UGAN: 1) achieves state-of-the-art performance among other deep generative models, and 2) is robust to variations in the amount of labeled data used for training.
Code (0)
등록된 구현이 없습니다.
Tasks
image-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Fast adversarial training for semi-supervised learning
In semi-supervised learning, Bad GAN approach is one of the most attractive method due to the intuitional simplicity and powerful performances. Bad GAN learns a classifier with bad samples distributed on complement of th…
Density EstimationUnderstanding and Improving Virtual Adversarial Training
In semi-supervised learning, virtual adversarial training (VAT) approach is one of the most attractive method due to its intuitional simplicity and powerful performances. VAT finds a classifier which is robust to data pe…
Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
Recently, semi-supervised learning methods based on generative adversarial networks (GANs) have received much attention. Among them, two distinct approaches have achieved competitive results on a variety of benchmark dat…
General ClassificationGenerative Adversarial NetworkImage GenerationSemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
Adversarial attack has garnered considerable attention due to its profound implications for the secure deployment of robots in sensitive security scenarios. To potentially push for advances in the field, this paper studi…
Adversarial AttackGood Semi-supervised Learning that Requires a Bad GAN
Semi-supervised learning methods based on generative adversarial networks (GANs) obtained strong empirical results, but it is not clear 1) how the discriminator benefits from joint training with a generator, and 2) why g…
General ClassificationSemi-Supervised Image Classification