Affiliation:
1. School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, Sichuan, P. R. China
Abstract
The performance of salient object detection (SOD) has been significantly advanced by using deep convolutional networks. However, it largely depends on the high cost of pixel-level annotations. To reduce human effort while improving the prediction accuracy, we propose a novel two-phase learning framework. The weakly supervised information in terms of scribbles is provided as initial labels. Then, as the first phase, high-quality pseudo-labels are generated by mapping scribbles onto object/object-part contours. These contour maps are predicted by the hierarchical contour detection algorithm, providing superior accuracy and smoothness. In the second phase, a deep neural network is alternately trained and predicted. The pseudo-labels are refined in an iterated process, where a conditional random field (CRF) model and a filter module are designed to promote the performance. Extensive experiments on five benchmarks show that our framework can achieve comparable results with the state-of-the-art fully and weakly supervised methods.
Funder
National Natural Science Foundation of China
Sichuan Science and Technology Program
Natural Science Foundation of Sichuan China
Fundamental Research Funds for the Central Universities
Publisher
World Scientific Pub Co Pte Ltd
Subject
Artificial Intelligence,Computer Vision and Pattern Recognition,Software