Abstract:
In view of the detail feature loss issue existing in the complex scenario of existing saliency detection algorithms, a fusion method of multi-layer sub-network cascade hybrid information flows is proposed in this paper. We first use the FCNs backbone network to obtain multi-scale features. Through the multi-layer sub-network layering mining to build a cascading network framework, the context information of the characteristic of each level is fully used. The detection and segmentation tasks are processed jointly. Multi-scale features are integrated by hybrid information flows, and more characteristic information with discernment is learned step by step. Finally, the embedded attention mechanism effectively compensates the deep semantic information as a mask, and further distinguishes the foreground and the messy background. Compared with the existing 9 algorithms on the basis of the 6 public datasets, the running speed of the proposed algorithm can reach 20.76 frames and the experimental results are generally optimal on 5 evaluation indicators, even for the challenging new dataset SOC. The proposed method is obviously better than the classic algorithm. Experimental results were improved by 1.96%, 3.53%, 0.94%, and 0.26% for F-measure, weighted F-measure, S-measure, and E-measure, respectively. These experimental results show that the demonstrating the proposed model has higher accuracy and robustness and can be suitable for more complex environments, the proposed framework improves the performance significantly for state-of-the-art models on a series of datasets.
E-mail Alert
RSS
Abstract: In view of the detail feature loss issue existing in the complex scenario of existing saliency detection algorithms, a fusion method of multi-layer sub-network cascade hybrid information flows is proposed in this paper. We first use the FCNs backbone network to obtain multi-scale features. Through the multi-layer sub-network layering mining to build a cascading network framework, the context information of the characteristic of each level is fully used. The detection and segmentation tasks are processed jointly. Multi-scale features are integrated by hybrid information flows, and more characteristic information with discernment is learned step by step. Finally, the embedded attention mechanism effectively compensates the deep semantic information as a mask, and further distinguishes the foreground and the messy background. Compared with the existing 9 algorithms on the basis of the 6 public datasets, the running speed of the proposed algorithm can reach 20.76 frames and the experimental results are generally optimal on 5 evaluation indicators, even for the challenging new dataset SOC. The proposed method is obviously better than the classic algorithm. Experimental results were improved by 1.96%, 3.53%, 0.94%, and 0.26% for F-measure, weighted F-measure, S-measure, and E-measure, respectively. These experimental results show that the demonstrating the proposed model has higher accuracy and robustness and can be suitable for more complex environments, the proposed framework improves the performance significantly for state-of-the-art models on a series of datasets.
