Open AccessSaliency Prediction Based On Lightweight Attention Mechanism
Author(s) -
Yu Wang,
Man Zhu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1486/7/072066
Subject(s) - artificial intelligence , pyramid (geometry) , computer science , salient , saliency map , field (mathematics) , context (archaeology) , feature (linguistics) , pattern recognition (psychology) , pixel , mechanism (biology) , scale (ratio) , machine learning , mathematics , paleontology , linguistics , philosophy , geometry , physics , epistemology , quantum mechanics , pure mathematics , biology
Saliency prediction refers to an algorithm that extracts salient regions from natural scenes. In the field of deep learning, receptive field limits the accuracy of pixel classification and thus affects the accuracy of saliency prediction. This study proposes a new saliency prediction method that uses the improved feature pyramid attention (FPA) to gain multi-scale context information to solve the above-mentioned problems. FPA’s number of parameters and cost of calculation are also decreased. Experimental results show that this method can obtain more accurate results than the existing saliency prediction methods without increasing the calculation amount.