Multi-Task Adversarial Network For Disentangled Feature Learning
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)(2018)
摘要
We address the problem of image feature learning for the applications where multiple factors exist in the image generation process and only some factors are of our interest. We present a novel multi-task adversarial network based on an encoder-discriminator-generator architecture. The encoder extracts a disentangled feature representation for the factors of interest. The discriminators classify each of the factors as individual tasks. The encoder and the discriminators are trained cooperatively on factors of interest, but in an adversarial way on factors of distraction. The generator provides further regularization on the learned feature by reconstructing images with shared factors as the input image. We design a new optimization scheme to stabilize the adversarial optimization process when multiple distributions need to be aligned. The experiments on face recognition and font recognition tasks show that our method outperforms the state-of-the-art methods in terms of both recognizing the factors of interest and generalization to images with unseen variations.
更多查看译文
关键词
multitask adversarial network,individual tasks,disentangled feature representation,encoder-discriminator-generator architecture,image generation process,multiple factors,image feature,disentangled feature learning,font recognition tasks,multiple distributions,input image,shared factors,learned feature
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络