paper-with-me

Papers

Semi-supervised Learning using Adversarial Training with Good and Bad Samples

2019-10-18 · Wenyuan Li, Zichen Wang, Yuguang Yue, Jiayun Li, William Speier, Mingyuan Zhou, Corey W. Arnold

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.

📄 PDF Abstract BibTeX arXiv:1910.08540

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Fast adversarial training for semi-supervised learning

2018-09-27 · Dongha Kim, Yongchan Choi, Jae-Joon Han, Changkyu Choi 외

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 Estimation

Understanding and Improving Virtual Adversarial Training

2019-09-15 · Dongha Kim, Yongchan Choi, Yongdai Kim

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

2019-05-16 · Wenyuan Li, Zichen Wang, Jiayun Li, Jennifer Polson 외

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 Generation

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images

2024-07-13 · Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu

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 Attack

Good Semi-supervised Learning that Requires a Bad GAN

2017-05-27 · NeurIPS 2017 12 · Zihang Dai, Zhilin Yang, Fan Yang, William W. Cohen 외

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