高级检索
    刘欢, 郑庆华, 罗敏楠, 赵洪科, 肖阳, 吕彦章. 基于跨域对抗学习的零样本分类[J]. 计算机研究与发展, 2019, 56(12): 2521-2535. DOI: 10.7544/issn1000-1239.2019.20190614
    引用本文: 刘欢, 郑庆华, 罗敏楠, 赵洪科, 肖阳, 吕彦章. 基于跨域对抗学习的零样本分类[J]. 计算机研究与发展, 2019, 56(12): 2521-2535. DOI: 10.7544/issn1000-1239.2019.20190614
    Liu Huan, Zheng Qinghua, Luo Minnan, Zhao Hongke, Xiao Yang, Lü Yanzhang. Cross-Domain Adversarial Learning for Zero-Shot Classification[J]. Journal of Computer Research and Development, 2019, 56(12): 2521-2535. DOI: 10.7544/issn1000-1239.2019.20190614
    Citation: Liu Huan, Zheng Qinghua, Luo Minnan, Zhao Hongke, Xiao Yang, Lü Yanzhang. Cross-Domain Adversarial Learning for Zero-Shot Classification[J]. Journal of Computer Research and Development, 2019, 56(12): 2521-2535. DOI: 10.7544/issn1000-1239.2019.20190614

    基于跨域对抗学习的零样本分类

    Cross-Domain Adversarial Learning for Zero-Shot Classification

    • 摘要: 零样本学习旨在识别具有少量、甚至没有训练样本的未见类,这些类与可见类遵循不同的数据分布.最近,随着深度神经网络在跨模态生成方面的成功,使用合成的样本对未见数据进行分类取得了巨大突破.现有方法通过共享生成器和解码器,联合传统生成对抗网络和变分自编码器来实现样本的合成.然而,由于这2种生成网络产生的数据分布不同,联合模型合成的数据遵循复杂的多域分布.针对这个问题,提出跨域对抗生成网络(CrossD-AGN),将传统生成对抗网络和变分自编码器有机结合起来,基于类级语义信息为未见类合成样本,从而实现零样本分类.提出跨域对抗学习机制,引入2个对称的跨域判别器,通过判断合成样本属于生成器域分布还是解码器域分布,促使联合模型中的生成器/解码器不断优化,提高样本合成能力.在多个真实数据集上进行了广泛的实验,结果表明了所提出方法在零样本学习上的有效性和优越性.

       

      Abstract: Zero-shot learning (ZSL) aims to recognize novel categories, which have few or even no sample for training and follow a different distribution from seen classes. With the recent advances of deep neural networks on cross-modal generation, encouraging breakthroughs have been achieved on classifying unseen categories with their synthetic samples. Extant methods synthesize unseen samples with the combination of generative adversarial nets (GANs) and variational auto-encoder (VAE) by sharing the generator and the decoder. However, due to the different data distributions produced by these two kinds of generative models, fake samples synthesized by the joint model follow the complex multi-domain distribution instead of satisfying a single model distribution. To address this issue, in this paper we propose a cross-domain adversarial generative network (CrossD-AGN) to integrate the traditional GANs and VAE into a unified framework, which is able to generate unseen samples based on the class-level semantics for zero-shot classification. We propose two symmetric cross-domain discriminators along with the cross-domain adversarial learning mechanism to learn to determine whether a synthetic sample is from the generator-domain or the decoder-domain distribution, so as to drive the generator/decoder of the joint model to improve its capacity of synthesizing fake samples. Extensive experimental results over several real-world datasets demonstrate the effectiveness and superiority of the proposed model on zero-shot visual classification.

       

    /

    返回文章
    返回