Paper Info
Title
Delving Into The Impact Of Saliency Detector: A Gemininet For Accurate Saliency Detection
Abstract
Although plenty of saliency detection methods based on CNNs have shown impressive performance, we observe that these methods adopt single-scale convolutional layers as saliency detectors after extracting features to predict saliency maps, which will cause serious missed detection especially those targets having small scales, irregular shapes and sporadic locations in complex scenario of multi-target graphs. In addition, the edges of salient objects predicted by these methods are often confused with their background, causing these partial regions to be very blurred. In order to deal with these issues, we delved into the impact of diverse unified detectors based on convolutional layers and nearest neighbor optimization on saliency detection. It was found that (1) the flattened design contributes to the improvement of accuracy, but due to the inherent characteristics of convolutional layers, it is not the effective way to solve the problems; (2) Nearest neighbor optimization is beneficial to remove background regions from salient objects and restore the missing sections while refining their boundaries, yielding a more reliable final prediction. With the progress of these studies, we built a GeminiNet for accurate saliency detection. Quantitative and qualitative experiments on six benchmark datasets demonstrate that our proposed GeminiNet performs favorably against the state-of-the-art methods under different evaluation metrics.
Year
DOI
Venue
2019
10.1007/978-3-030-30508-6_28
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: IMAGE PROCESSING, PT III
Keywords
DocType
Volume
Deep learning, Convolutional neural network, Image segmentation
Conference
11729
ISSN
Citations 
PageRank 
0302-9743
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Tao Zheng101.35
Bo Li200.68
Delu Zeng316411.46
Zhiheng Zhou44323.53