Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCN based methods still suffer from continuous striding and pooling operations leading to loss of spatial structure and blurred edges. To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge guided feature learning for accurate salient object detection. In a specific, we extract hierarchical global and local information in FCN to incorporate non-local features for effective feature representations. To preserve good boundaries of salient objects, we propose a guidance block to embed edge prior knowledge into hierarchical feature maps. The guidance block not only performs feature-wise manipulation but also spatial-wise transformation for effective edge embeddings. Our model is trained on the MSRA-B dataset and tested on five popular benchmark datasets. Comparing with the state-of-the-art methods, the proposed method achieves the best performance on all datasets.

中文翻译：

---

用于显着目标检测的边缘引导非局部全卷积网络

近年来，全卷积神经网络（FCN）凭借高级语义特征提取被广泛应用于显着目标检测，但现有的基于 FCN 的方法仍然存在连续跨步和池化操作，导致空间结构丢失和边缘模糊。为了保持显着对象的清晰边缘结构，我们提出了一种新颖的边缘引导非局部 FCN（ENFNet）来执行边缘引导特征学习，以实现准确的显着对象检测。具体来说，我们在 FCN 中提取分层的全局和局部信息，以结合非局部特征以进行有效的特征表示。为了保留显着对象的良好边界，我们提出了一个引导块，将边缘先验知识嵌入到分层特征图中。引导块不仅执行特征操作，还执行有效边缘嵌入的空间转换。我们的模型在 MSRA-B 数据集上进行了训练，并在五个流行的基准数据集上进行了测试。与最先进的方法相比，所提出的方法在所有数据集上都实现了最佳性能。