• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of visual communication & image representation >WavNet - Visual saliency detection using Discrete Wavelet Convolutional Neural Network
【24h】

WavNet - Visual saliency detection using Discrete Wavelet Convolutional Neural Network

机译：Wavnet - 使用离散小波卷积神经网络的视觉显着性检测

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.
机译：在最近的图像和视频分析的进步中，图像中的突出区域的检测成为初始步骤。这在决定这种算法的性能方面起着至关重要的作用。在这项工作中，采用一种多分析特征提取（MRFE）技术，其利用用于产生特征的离散小波卷积神经网络（DWCNN）。增强功能提取（EFE）模块从DWCNN的高级功能提取附加功能，用于框架频道以及用于产生语境注意图的空间注意模型。还提出了一种新的混合损失功能，这是平衡跨熵（BCE）损失和边缘基于边缘的结构相似性（ESSIM）损失的组合，从而有效地识别和区分具有透明边界的凸极区域。该方法用五种不同的基准数据集进行详尽测试，并且被证明优于现有的最先进的方法，其最小的平均值误差（MAE）为0.03和F法为0.956。

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