Dual-Branch Feature Fusion Network for Salient Object Detection
Open Access
Abstract
Proper features matter for salient object detection. Existing methods mainly focus on designing a sophisticated structure to incorporate multi-level features and filter out cluttered features. We present the dual-branch feature fusion network (DBFFNet), a simple effective framework mainly composed of three modules: global information perception module, local information concatenation module and refinement fusion module. The local information of a salient object is extracted from the local information concatenation module. The global information perception module exploits the U-Net structure to transmit the global information layer by layer. By employing the refinement fusion module, our approach is able to refine features from two branches and detect salient objects with final details without any post-processing. Experiments on standard benchmarks demonstrate that our method outperforms almost all of the state-of-the-art methods in terms of accuracy, and achieves the best performance in terms of speed under fair settings. Moreover, we design a wide-field optical system and combine with DBFFNet to achieve salient object detection with large field of view.Keywords
Funding Information
- Zhejiang University Basic Research Project (KM20190444)
This publication has 11 references indexed in Scilit:
- Advancement of Machine Intelligence in Interactive Medical Image AnalysisAlgorithms for Intelligent Systems, 2020
- Image Segmentation Using Deep Learning Techniques in Medical ImagesAlgorithms for Intelligent Systems, 2019
- Attentive Feedback Network for Boundary-Aware Salient Object Detection2019
- Wide field-of-view crossed Dragone optical system using anamorphic aspherical surfacesApplied Optics, 2018
- Saliency detection by multi-context deep learning2015
- Fully convolutional networks for semantic segmentation2015
- SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object DetectionInternational Journal of Computer Vision, 2015
- Context-Aware Saliency DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Frequency-tuned salient region detection2009
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998