Joint Learning of Generative Translator and Classifier for Visually Similar Classes

Abstract

In this paper, we propose a Generative Translation Classification Network (GTCN) for improving visual classification accuracy in settings where classes are visually similar and data is scarce. For this purpose, we propose joint learning from a scratch to train a classifier and a generative stochastic translation network end-to-end. The translation network is used to perform on-line data augmentation across classes, whereas previous works have mostly involved domain adaptation. To help the model further benefit from this data-augmentation, we introduce an adaptive fade-in loss and a quadruplet loss. We perform experiments on multiple datasets to demonstrate the proposed method's performance in varied settings. Of particular interest, training on 40% of the dataset is enough for our model to surpass the performance of baselines trained on the full dataset. When our architecture is trained on the full dataset, we achieve comparable performance with state-of-the-art methods despite using a light-weight architecture.

arXiv comment14 pages, 17 figures, 13 tables

References in corpus (18)

• Auto-Encoding Variational Bayes
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Conditional Generative Adversarial Nets
• Generative Adversarial Networks: An Overview
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Toward Multimodal Image-to-Image Translation
• Data Augmentation Generative Adversarial Networks
• Adversarially Learned Inference
• Semi-Supervised Learning with Generative Adversarial Networks
• Unsupervised Cross-Domain Image Generation
• Learn Convolutional Neural Network for Face Anti-Spoofing
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
• Good Semi-supervised Learning that Requires a Bad GAN
• Triple Generative Adversarial Nets
• Triangle Generative Adversarial Networks
• Face Spoofing Detection by Fusing Binocular Depth and Spatial Pyramid Coding Micro-Texture Features
• Face Flashing: a Secure Liveness Detection Protocol based on Light Reflections