Light-weighted Saliency Detection with Distinctively Lower Memory Cost and Model Size

Abstract

Deep neural networks (DNNs) based saliency detection approaches have succeed in recent years, and improved the performance by a great margin via increasingly sophisticated network architecture. Despite the performance improvement, the computational cost is excessively high for such low level visual task. In this work, we propose a light-weighted saliency detection approach with distinctively lower runtime memory cost and model size. We evaluated the performance of our approach on multiple benchmark datasets, and achieved competitive results comparing with state-of-the-art methods on multiple metrics. We also evaluated the computational cost of our approach with multiple measurements. The runtime memory cost of our approach is 42 to 99 times fewer comparing with the previous DNNs based methods. The model size of our approach is 63 to 129 times smaller, and takes less than 1 Megabytes storage space with out any deep compression technique.

7 pages, 4 figures. arXiv admin note: text overlap with arXiv:1809.00644

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
• DeepGaze II: Reading fixations from deep features trained on object recognition
• CAT2000: A Large Scale Fixation Dataset for Boosting Saliency Research