Feature extraction and fusion network for salient object detection

In the salient object detection (SOD) models based on convolutional neural network (CNN), the high-level semantic features and low-level features of the image are effectively fused and complementary, which can effectively improve the performance of SOD. However, there are usually great differences between high-level semantic features and low-level features, and low-level features are often rich in noise. How to make full use of different features and avoid noise interference is a hot issue for researchers. Different from the traditional methods, this paper proposes a novel feature extraction and fusion network (EFNet). By setting a middle-level feature extraction module as the medium for the fusion of high-level semantic features and low-level image features, this special module integrates the two by reducing the difference between low-level image features and deep semantic features; In addition, a feature enhancement module is applied to enhance the image features, and the proposed SOD method can obtain good performance. Experimental results on five benchmark datasets show that the proposed method outperforms 15 state-of-the-art methods on five important evaluation metrics. Code will be available at: https://github.com/dc3234/EFNet.