Label Geometry Aware Discriminator for Conditional Generative Networks

by   Suman Sapkota, et al.

Multi-domain image-to-image translation with conditional Generative Adversarial Networks (GANs) can generate highly photo realistic images with desired target classes, yet these synthetic images have not always been helpful to improve downstream supervised tasks such as image classification. Improving downstream tasks with synthetic examples requires generating images with high fidelity to the unknown conditional distribution of the target class, which many labeled conditional GANs attempt to achieve by adding soft-max cross-entropy loss based auxiliary classifier in the discriminator. As recent studies suggest that the soft-max loss in Euclidean space of deep feature does not leverage their intrinsic angular distribution, we propose to replace this loss in auxiliary classifier with an additive angular margin (AAM) loss that takes benefit of the intrinsic angular distribution, and promotes intra-class compactness and inter-class separation to help generator synthesize high fidelity images. We validate our method on RaFD and CIFAR-100, two challenging face expression and natural image classification data set. Our method outperforms state-of-the-art methods in several different evaluation criteria including recently proposed GAN-train and GAN-test metrics designed to assess the impact of synthetic data on downstream classification task, assessing the usefulness in data augmentation for supervised tasks with prediction accuracy score and average confidence score, and the well known FID metric.


page 11

page 12

page 13

page 14

page 15

page 16

page 17

page 18


FA-GAN: Feature-Aware GAN for Text to Image Synthesis

Text-to-image synthesis aims to generate a photo-realistic image from a ...

Classification Accuracy Score for Conditional Generative Models

Deep generative models (DGMs) of images are now sufficiently mature that...

DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion

Class-conditional image generation using generative adversarial networks...

Generative Adversarial Network Based Synthetic Learning and a Novel Domain Relevant Loss Term for Spine Radiographs

Problem: There is a lack of big data for the training of deep learning m...

UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs

We present an approach to quantifying both aleatoric and epistemic uncer...

Effective Data Augmentation with Multi-Domain Learning GANs

For deep learning applications, the massive data development (e.g., coll...

Inducing Optimal Attribute Representations for Conditional GANs

Conditional GANs are widely used in translating an image from one catego...

Please sign up or login with your details

Forgot password? Click here to reset