Rich‐scale feature fusion network for salient object detection. Issue 3 (16th November 2022)

• Record Type: Journal Article
• Authors: Sun, Fengming; Cui, Junjie; Yuan, Xia; Zhao, Chunxia
• Is Part Of: IET image processing. Volume 17:Issue 3(2023)
• Page Start: 794
• Page End: 806
• Publication Date: 2022-11-16
• Subjects: feature fusion -- global feature enhance -- multi‐scale feature -- salient object detection; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12673
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: Fully convolutional neural networks‐based salient object detection has recently achieved great success with its performance benefits from the effective use of multi‐layer features. Based on this, most of the existing saliency detectors designed complex network structures to fuse the multi‐level features generated by the backbone network. However, the variable scale and complex shape of the target are always a great challenge for saliency detection tasks. In this paper, the authors propose a Rich‐scale Feature Fusion Network (RFFNet) for salient object detection. The authors design a rich‐scale feature interactive fusion module to obtain more efficient features from the multi‐scale features. Moreover, the global feature enhance module is used to extract features with better characterization for the final saliency prediction. Extensive experiments performed on five benchmark datasets demonstrate that the proposed method can achieve satisfactory results on different evaluation metrics compared to other state‐of‐the‐art salient object detection approaches.