Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection

Youbao Tang, Xiangqian Wu, Wei Bu
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, the local, global, and contextual information of salient objects is important to obtain a high quality salient map. To achieve this goal, the DSRCNN is designed based on VGGNet-16. Firstly, the recurrent connections are incorporated into each convolutional layer, which can make
more » ... e model more powerful for learning the contextual information. Secondly, side-output layers are added to conduct the deeplysupervised operation, which can make the model learn more discriminative and robust features by effecting the intermediate layers. Finally, all of the side-outputs are fused to integrate the local and global information to get the final saliency detection results. Therefore, the DSRCNN combines the advantages of recurrent convolutional neural networks and deeply-supervised nets. The DSRCNN model is tested on five benchmark datasets, and experimental results demonstrate that the proposed method significantly outperforms the state-of-the-art saliency detection approaches on all test datasets.
doi:10.1145/2964284.2967250 dblp:conf/mm/TangWB16 fatcat:xjobladncze45luax2evr6m3sq