Feature Selection Method Guided by Attention Mechanism for Image Classification
首发时间:2018-07-31
Abstract:In recent years, significant progresses have been made in the field of deep learning, especially in visual image classification. The features learned automatically by feed-forward deep convolutional neural networks (CNNs) are important for image classification. However, there is not much research on the spatial relationship of images in despite of a huge amount of work on constructing different network structures to improve classification accuracy. Therefore, in this paper, we propose a method for classifying images with saliency information and background information. We demonstrate that both saliency features and background features have an important influence on image classification. We firstly obtain attention heat map and features from CNN network. Secondly, we separate the features into saliency features and background features inspired by attention heat map. Then, we adopt several pooling strategies to process saliency and background features. Finally, we classify image by training a SVM classifier. Especially, we get effective improvements in Calthech-256 with 78.15\% accuracy and PASCAL VOC 2012 with 84.1\% mAP, demonstrating the effectiveness of our proposed method.
keywords: Feature selection Attention Image classification
点击查看论文中文信息
注意机制引导下的面向图像分类的特征选择方法
摘要:近年来,深度学习领域取得了重大进展,特别是在视觉图像分类领域。前馈卷积神经网络自动学习的特征对于图像分类任务产生了很好的结果。然而,尽管现在很多方法在构建不同的网络结构以提高分类准确率方面进行了大量工作,但是对于图像空间关系的研究并不多。因此,本文提出了一种使用显著信息和背景信息对图像进行分类的方法。我们证明了显著特征和背景特征对图像分类都有重要影响。我们首先从卷积神经网络获取热度图和特征。其次,我们将这些特征分为显著特征和背景特征。然后,我们采用几种策略来处理这些特征。最后,我们通过训练SVM分类器对图像进行分类。我们在Calthech-256数据集上得到了78.15\%准确率并且在PASCAL VOC 2012数据集上得到了84.1\% 的平均准确率,这些结果证明了我们提出的方法的有效性。
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
注意机制引导下的面向图像分类的特征选择方法
评论
全部评论0/1000