首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Separability and Compactness Network for Image Recognition and Superresolution
【24h】

Separability and Compactness Network for Image Recognition and Superresolution

机译:用于图像识别和超分辨率的可分离性和紧凑性网络

获取原文
获取原文并翻译 | 示例
           

摘要

Convolutional neural networks (CNNs) have wide applications in pattern recognition and image processing. Despite recent advances, much remains to be done for CNNs to learn a better representation of image samples. Therefore, constant optimizations should be provided on CNNs. To achieve a good performance on classification, intuitively, samples' interclass separability, or intraclass compactness should be simultaneously maximized. Accordingly, in this paper, we propose a new network, named separability and compactness network (SCNet) to rectify this problem. SCNet minimizes the softmax loss and the distance between features of samples from the same class under a jointly supervised framework, resulting in simultaneous maximization of interclass separability and intraclass compactness of samples. Furthermore, considering the convenience and the efficiency of the cosine similarity in face recognition tasks, we incorporate it into SCNet's distance metric to enable sample features from the same class to line up in the same direction and those from different classes to have a large angle of separation. We apply SCNet to three different tasks: visual classification, face recognition, and image superresolution. Experiments on both public data sets and real-world satellite images validate the effectiveness of our SCNet.
机译:卷积神经网络(CNN)在模式识别和图像处理中具有广泛的应用。尽管有最新进展,但CNN要学习更好的图像样本表示,还有很多工作要做。因此,应在CNN上提供恒定的优化。为了在分类上获得良好的性能,直觉上,样品的类间可分离性或类内紧实度应同时最大化。因此,在本文中,我们提出了一个名为可分离性和紧凑性网络(SCNet)的新网络来纠正此问题。 SCNet在共同监督的框架下将softmax损失和同一类样本的特征之间的距离最小化,从而使样本之间的类间可分离性和样本内紧凑性同时最大化。此外,考虑到人脸识别任务中余弦相似度的便利性和效率,我们将其合并到SCNet的距离度量中,以使来自相同类别的样本特征可以沿相同方向排列,而来自不同类别的样本特征具有较大的分离。我们将SCNet应用于三个不同的任务:视觉分类,人脸识别和图像超分辨率。在公共数据集和真实世界的卫星图像上进行的实验都验证了我们SCNet的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号