Salient object detection is usually used as a preprocessing step to facilitate a variety of subsequent applications which should take little time cost. With the quick development of deep learning recently, profound progresses have been made to achieve a new state-of-the-art performance. However, the learned features of the existing deep learning-based methods are not accurate enough thus leading to unsatisfactory detection in complex scenes, such as low contrast or very similar between salient object and background region and multiple (small) salient objects with diverse characteristics. In addition, some post-processing techniques are usually needed for refinement, which is time consuming. To address these issues, this paper presents an efficient fully convolutional salient object detection network. Specifically, we first introduce a visual attention mechanism to guide feature learning in side output layers. In detail, attention weight is employed in a top-down manner which can bridge high level semantic information to help shallow layers better locate salient objects and also filter out noisy response in the background region. Second, we propose a residual refinement network to fuse the learned multilevel features gradually. Not to simply add or concatenate them step by step as previous works, we introduce a second-order term into element-wise addition to learn stage-wise residual features for refinement. Such a second-order term not only benefits efficient gradient propagation but also increases network nonlinearity. Extensive experiments on seven standard benchmarks demonstrate that the proposed approach achieves consistently superior performance and performs well on small salient object detection in comparison with the very recent state-of-the-arts, especially in the metric of structure-measure.

Benefiting from the quick development of deep convolutional neural networks, especially fully convolutional neural networks (FCNs), remarkable progresses have been achieved on salient object detection recently. Nevertheless, these FCNs based methods are still challenging to generate high resolution saliency maps, and also not applicable for subsequent applications due to their heavy model weights. In this paper, we propose a compact and efficient deep network with high accuracy for salient object detection. Firstly, we propose two strategies for initial prediction, one is a new designed multi-scale context module, the other is incorporating hand-crafted saliency priors. Secondly, we employ residual learning to refine it progressively by only learning the residual in each side-output, which can be achieved with few convolutional parameters, therefore leads to high compactness and high efficiency. Finally, we further design a novel reverse attention block to guide side-output residual learning in a top-down manner. Specifically, the current predicted salient regions are erased from each side-output feature, thus the missing object parts and details can be efficiently learned from these unerased regions, which results in high resolution and accuracy. Extensive experimental results on seven benchmark datasets demonstrate that the proposed network performs favorably against the state-of-the-art methods, and with advantages in terms of simplicity, efficiency and model size.