ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2020, Vol. 57 ›› Issue (3): 604-615.doi: 10.7544/issn1000-1239.2020.20190256

• 人工智能 • 上一篇    下一篇

基于特征对抗对的视觉特征归因网络研究

张宪1,史沧红2,李孝杰1   

  1. 1(成都信息工程大学计算机学院 成都 610103);2(西南交通大学信息科学与技术学院 成都 611765) (zhangxian317@gmail.com)
  • 出版日期: 2020-03-01
  • 基金资助: 
    国家自然科学基金项目(61602066,61702058);四川省科技厅杰出青年科技人才项目(19JCQN0003);四川省教育厅自然科学重点项目(17ZA0063);成都信息工程大学校中青年学术带头人科研基金项目(J201704)

Visual Feature Attribution Based on Adversarial Feature Pairs

Zhang Xian1, Shi Canghong2, Li Xiaojie1   

  1. 1(College of Computer Science, Chengdu University of Information Technology, Chengdu 610103);2(School of Information Science and Technology, Southwest Jiatong University, Chengdu 611765)
  • Online: 2020-03-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (61602066, 61702058), the Outstanding Young Talents Project of Sichuan Provincal Department of Science and Technology (19JCQN0003), the Key Project of Natural Science of Sichuan Provincial Education Department (17ZA0063), and the Natural Science Foundation for Young Scientists of Chengdu University of Information Technology (J201704).

摘要: 可视化图像关键特征区域是计算机视觉一个重要而需要深入研究的问题.图像关键特征区域可视化的技术已经在弱监督定位和理解数据隐藏特征的领域中得到广泛应用.近年来,基于神经网络分类器的特征定位显示已成为最新的技术,并且通常用于医学和自然图像数据集上.但存在特征定位显示不精确的缺陷.针对传统神经网络分类器在可视化图像关键特征区域标注方法上的局限性,提出了一种基于生成对抗对特征的关键特征区域可视化方法(即视觉特征归因方法).该方法通过构造关键特征区域对抗对,采用生成和鉴别对抗网络生成关键特征区域,可有效过滤冗余信息并实现精准定位,有效解决了疾病特征可视化问题.在该方法中,为了解决传统生成对抗网络难以达到负载均衡的缺陷,采用了Wasserstein距离解决协调其训练平衡的问题,同时使用梯度惩罚加速收敛过程.在人工合成数据集、肺部数据集和心脏数据集上的实验结果表明,提出的方法在视觉显示的定性和定量的问题中,均产生了理想的真实效果图,非常接近观察到的效果.

关键词: 生成对抗对, 特征可视化, 弱监督, Wasserstein生成对抗网络, 梯度惩罚

Abstract: Visualizing the key feature of images is an important issue and requires in-depth study for computer vision. Its application ranges from weak supervision in the object localization task to understanding in the hidden features of the data. In medical and natural images data sets, the convolutional neural network-based model has become the latest technology for visualizing the regions of input, which are important for predictions from these models or visual explanations. However, their feature location is not accurate. In view of the limitations of the traditional neural network classifier in the region of the visual image key characteristics, we propose an effective adversarial feature pairs based method for visual feature attribution. In the proposed method, We firstly construct adversarial pair of key feature areas as the input of generative adversarial network (GAN). This makes the generator produce high corresponding key features, and can effectively filter redundant information and achieve accurate position. However, traditional GAN is difficult to produce images that are similar to real images. Therefore, Wasserstein distance and gradient penalty are employed to solve the problem and accelerate the convergence process. Experimental results on synthetic datasets, lung datasets and heart datasets show that our proposed method produces convincing real-world effects in both qualitative and quantitative visual displays.

Key words: adversarial feature pairs, feature visualization, weak supervision, Wasserstein generative adversarial network, gradient penalty

中图分类号: