Deepside: A general deep framework for salient object detection
Artikel i vetenskaplig tidskrift, 2019

Deep learning-based salient object detection techniques have shown impressive results compared to con- ventional saliency detection by handcrafted features. Integrating hierarchical features of Convolutional Neural Networks (CNN) to achieve fine-grained saliency detection is a current trend, and various deep architectures are proposed by researchers, including “skip-layer” architecture, “top-down” architecture, “short-connection” architecture and so on. While these architectures have achieved progressive improve- ment on detection accuracy, it is still unclear about the underlying distinctions and connections between these schemes. In this paper, we review and draw underlying connections between these architectures, and show that they actually could be unified into a general framework, which simply just has side struc- tures with different depths. Based on the idea of designing deeper side structures for better detection accuracy, we propose a unified framework called Deepside that can be deeply supervised to incorporate hierarchical CNN features. Additionally, to fuse multiple side outputs from the network, we propose a novel fusion technique based on segmentation-based pooling, which severs as a built-in component in the CNN architecture and guarantees more accurate boundary details of detected salient objects. The effectiveness of the proposed Deepside scheme against state-of-the-art models is validated on 8 benchmark datasets.

Salient object detection Convolutional neural network Side structure Deep supervision

Författare

Keren Fu

Sichuan University

Qijun Zhao

Sichuan University

Irene Yu-Hua Gu

Chalmers, Elektroteknik

Jie Yang

Shanghai Jiao Tong University

Neurocomputing

0925-2312 (ISSN) 18728286 (eISSN)

Vol. 356 69-82

Ämneskategorier

Annan data- och informationsvetenskap

Bioinformatik (beräkningsbiologi)

Elektroteknik och elektronik

Datavetenskap (datalogi)

Datorseende och robotik (autonoma system)

DOI

10.1016/j.neucom.2019.04.062

Mer information

Senast uppdaterat

2019-06-11