paper-with-me

Papers

Spatially Decomposed Hinge Adversarial Loss by Local Gradient Amplifier

2021-01-01 · Sanghun Kim, Seungkyu Lee

Generative Adversarial Networks (GANs) have achieved large attention and great success in various research areas, but it still suffers from training instability. Recently hinge adversarial loss for GAN is proposed that incorporates the SVM margins where real and fake samples falling within the margins contribute to the loss calculation. In a generator training step, however, fake samples outside of the margins that partially include unrealistic local patterns are ignored. In this work, we propose local gradient amplifier(LGA) which realizes spatially decomposed hinge adversarial loss for improved generator training. Spatially decomposed hinge adversarial loss applies different margins for different spatial regions extending overall margin space toward all fake samples asymmetrically. Our proposed method is evaluated on several public benchmark data sets compared to state of the art methods showing outstanding stability in training GANs.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Similar Papers 제목 키워드 기반

Achieving robustness in classification using optimal transport with hinge regularization

2020-06-11 · CVPR 2021 1 · Mathieu Serrurier, Franck Mamalet, Alberto González-Sanz, Thibaut Boissin 외

Adversarial examples have pointed out Deep Neural Networks vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustness, but make them harder to learn with cl…

Adversarial RobustnessBinary ClassificationGeneral Classification

Adversarial Multiclass Classification: A Risk Minimization Perspective

2016-12-01 · NeurIPS 2016 12 · Rizal Fathony, Anqi Liu, Kaiser Asif, Brian Ziebart

Recently proposed adversarial classification methods have shown promising results for cost sensitive and multivariate losses. In contrast with empirical risk minimization (ERM) methods, which use convex surrogate losses …

ClassificationGeneral Classification

Kernel Support Vector Machine Classifiers with the $\ell_0$-Norm Hinge Loss

2023-06-24 · Rongrong Lin, Yingjia Yao, YuLan Liu

Support Vector Machine (SVM) has been one of the most successful machine learning techniques for binary classification problems. The key idea is to maximize the margin from the data to the hyperplane subject to correct c…

Binary Classification

MAGAN: Margin Adaptation for Generative Adversarial Networks

2017-04-12 · Ruohan Wang, Antoine Cully, Hyung Jin Chang, Yiannis Demiris

We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function. We estimate the …

Image Generation

Adversarial Surrogate Losses for Ordinal Regression

2017-12-01 · NeurIPS 2017 12 · Rizal Fathony, Mohammad Ali Bashiri, Brian Ziebart

Ordinal regression seeks class label predictions when the penalty incurred for mistakes increases according to an ordering over the labels. The absolute error is a canonical example. Many existing methods for this task r…

Binary ClassificationGeneral Classificationregression