TY - GEN
T1 - R3Net
T2 - 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
AU - Deng, Zijun
AU - Hu, Xiaowei
AU - Zhu, Lei
AU - Xu, Xuemiao
AU - Qin, Jing
AU - Han, Guoqiang
AU - Heng, Pheng Ann
N1 - Funding Information:
The work is supported by the Shenzhen Science and Technology Program (JCYJ20170413162256793), the Research Grants Council of the Hong Kong Special Administrative Region (Project no. CUHK 14225616), the Hong Kong Innovation and Technology Commission (Project no. ITS/304/16), NSFC (Grant No. 61772206, U1611461, 61472145), Special Fund of Science and Technology Research and Development on Application from Guangdong Province (Grant No. 2016B010124011), Guangdong High-level Personnel of Special Support Program (Grant No. 2016TQ03X319), and the Guangdong Natural Science Foundation (Grant No. 2017A030311027). Xiaowei Hu is funded by the Hong Kong Ph.D. Fellowship.
Publisher Copyright:
© 2018 International Joint Conferences on Artificial Intelligence. All right reserved.
PY - 2018
Y1 - 2018
N2 - Saliency detection is a fundamental yet challenging task in computer vision, aiming at highlighting the most visually distinctive objects in an image. We propose a novel recurrent residual refinement network (R3Net) equipped with residual refinement blocks (RRBs) to more accurately detect salient regions of an input image. Our RRBs learn the residual between the intermediate saliency prediction and the ground truth by alternatively leveraging the low-level integrated features and the high-level integrated features of a fully convolutional network (FCN). While the low-level integrated features are capable of capturing more saliency details, the high-level integrated features can reduce non-salient regions in the intermediate prediction. Furthermore, the RRBs can obtain complementary saliency information of the intermediate prediction, and add the residual into the intermediate prediction to refine the saliency maps. We evaluate the proposed R3Net on five widely-used saliency detection benchmarks by comparing it with 16 state-of-the-art saliency detectors. Experimental results show that our network outperforms our competitors in all the benchmark datasets.
AB - Saliency detection is a fundamental yet challenging task in computer vision, aiming at highlighting the most visually distinctive objects in an image. We propose a novel recurrent residual refinement network (R3Net) equipped with residual refinement blocks (RRBs) to more accurately detect salient regions of an input image. Our RRBs learn the residual between the intermediate saliency prediction and the ground truth by alternatively leveraging the low-level integrated features and the high-level integrated features of a fully convolutional network (FCN). While the low-level integrated features are capable of capturing more saliency details, the high-level integrated features can reduce non-salient regions in the intermediate prediction. Furthermore, the RRBs can obtain complementary saliency information of the intermediate prediction, and add the residual into the intermediate prediction to refine the saliency maps. We evaluate the proposed R3Net on five widely-used saliency detection benchmarks by comparing it with 16 state-of-the-art saliency detectors. Experimental results show that our network outperforms our competitors in all the benchmark datasets.
UR - http://www.scopus.com/inward/record.url?scp=85055128107&partnerID=8YFLogxK
M3 - Conference article published in proceeding or book
AN - SCOPUS:85055128107
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 684
EP - 690
BT - Proceedings of the 27th International Joint Conference on Artificial Intelligence, IJCAI 2018
A2 - Lang, Jerome
PB - International Joint Conferences on Artificial Intelligence
Y2 - 13 July 2018 through 19 July 2018
ER -