Biblio

Due to the continuous improvement of deep learning, saliency object detection based on deep learning has been a hot topic in computational vision. The Fully Convolutional Neural Network (FCNS) has become the mainstream method in salient target measurement. In this article, we propose a new end-to-end multi-level feature fusion module(MCFB), success-fully achieving the goal of extracting rich multi-scale global information by integrating semantic and detailed information. In our module, we obtain different levels of feature maps through convolution, and then cascade the different levels of feature maps, fully considering our global information, and get a rough saliency image. We also propose an optimization module upon our base module to further optimize the feature map. To obtain a clearer boundary, we use a self-defined loss function to optimize the learning process, which includes the Intersection-over-Union (IoU) losses, Binary Cross-Entropy (BCE), and Structural Similarity (SSIM). The module can extract global information to a greater extent while obtaining clearer boundaries. Compared with some existing representative methods, this method has achieved good results.

Previous saliency detection methods usually focus on extracting features to deal with the complex background in an image. However, these methods cannot effectively capture the semantic information of images. In recent years, Generative Adversarial Network (GAN) has become a prevalent research topic. Experiments show that GAN has ability to generate high quality images that look like natural images. Inspired by the effectiveness of GAN feature learning, we propose a novel multi-scale adversarial feature learning (MAFL) model for saliency detection. In particular, we model the complete framework of saliency detection is based on two deep CNN modules: the multi-scale G-network takes natural images as inputs and generates corresponding synthetic saliency map, and we designed a novel layer in D-network, namely a correlation layer, which is used to determine whether one image is a synthetic saliency map or ground-truth saliency map. Quantitative and qualitative experiments on three benchmark datasets demonstrate that our method outperforms seven state-of-the-art methods.