Refinet: A Deep Segmentation Assisted Refinement Network for Salient Object Detection
Artikel i vetenskaplig tidskrift, 2018

Deep convolutional neural networks (CNNs) recently have been successfully applied to saliency detection with improved performance on locating salient objects, as comparing to conventional saliency detection by handcrafted features.
Unfortunately, due to repeated sub-sampling operations inside CNNs such as pooling and convolution, many CNN-based saliency
models fail to maintain fine-grained spatial details and boundary structures of objects. To remedy this issue, this paper proposes
a novel end-to-end deep learning-based refinement model named Refinet, which is based on fully convolutional network augmented
with segmentation hypotheses. Intermediate saliency maps which are edge-aware are computed from segmentation-based pooling
and then cancatenating two streams into a fully convolutional network for effective fusion and refinement, leading to more precise object
details and boundaries. In addition, the resolution of feature maps in the proposed Refinet is carefully designed to guarantee sufficient
boundary clarity of the refined saliency output. Compared to widely employed dense conditional random field (CRF), Refinet
is able to enhance coarse saliency maps generated by existing models with more accurate spatial details, and its effectiveness is
demonstrated by experimental results on 7 benchmark datasets.

Image segmentation

Fully convolutional neural network

Refinement

Salient object detection

Författare

Keren Fu

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Signalbehandling

Qijun Zhao

Unknown organization

Irene Yu-Hua Gu

Chalmers, Elektroteknik, Signalbehandling och medicinsk teknik, Signalbehandling

IEEE Transactions on Multimedia

1520-9210 (ISSN)

Vol. accepted, 2018 13 pages-

Styrkeområden

Informations- och kommunikationsteknik

Transport

Ämneskategorier

Systemvetenskap

Elektroteknik och elektronik

Datorseende och robotik (autonoma system)