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.

在图像和视频分析的最新进展中，图像中显着区域的检测成为第一步。这在决定此类算法的性能方面起着至关重要的作用。在这项工作中，采用了一种利用离散小波卷积神经网络 (DWCNN) 生成特征的多分辨率特征提取 (MRFE) 技术。增强型特征提取 (EFE) 模块从 DWCNN 的高级特征中提取附加特征，这些特征用于构建通道和空间注意模型以生成上下文注意图。还提出了一种新的混合损失函数，它是平衡交叉熵 (BCE) 损失和基于边缘的结构相似性 (ESSIM) 损失的组合，可有效识别和分割具有清晰边界的显着区域。