MEAN: Multi-Edge Adaptation Network for Salient Object Detection Refinement

Recent advances in salient object detection adopting deep convolutional neural networks have achieved state-of-the-art performance. Salient object detection is task in computer vision to detect interesting objects. Most of the Convolutional Neural Network (CNN)-based methods produce plausible saliency outputs, yet with extra computational time. However in practical, the low computation algorithm is demanded. One approach to overcome this limitation is to resize the input into a smaller size to reduce the heavy computation in the backbone network. However, this process degrades the performance, and fails to capture the exact details of the saliency boundaries due to the downsampling process. A robust refinement strategy is needed to improve the final result where the refinement computation should be lower than that of the original prediction network. Consequently, a novel approach is proposed in this study using the original image gradient as a guide to detect and refine the saliency result. This approach lowers the computational cost by eliminating the huge computation in the backbone network, enabling flexibility for users in choosing a desired size with a more accurate boundary. The proposed method bridges the benefits of smaller computation and a clear result on the boundary. Extensive experiments have demonstrated that the proposed method is able to maintain the stability of the salient detection performance given a smaller input size with a desired output size and improvise the overall salient object detection result.