TY - GEN
T1 - FCSS
T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
AU - Kim, Seungryong
AU - Min, Dongbo
AU - Ham, Bumsub
AU - Jeon, Sangryul
AU - Lin, Stephen
AU - Sohn, Kwanghoon
N1 - Funding Information:
Acknowledgement. This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (R0124-16-0002, Emotional Intelligence Technology to Infer Human Emotion and Carry on Dialogue Accordingly). The work of B. Ham was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. 2017R1C1B2005584).
Funding Information:
This work was supported by Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (MSIP) (R0124-16-0002, Emotional Intelligence Technology to Infer Human Emotion and Carry on Dialogue Accordingly). The work of B. Ham was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (No. 2017R1C1B2005584).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/11/6
Y1 - 2017/11/6
N2 - We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. To robustly match points among different instances within the same object class, we formulate FCSS using local self-similarity (LSS) within a fully convolutional network. In contrast to existing CNN-based descriptors, FCSS is inherently insensitive to intra-class appearance variations because of its LSS-based structure, while maintaining the precise localization ability of deep neural networks. The sampling patterns of local structure and the self-similarity measure are jointly learned within the proposed network in an end-to-end and multi-scale manner. As training data for semantic correspondence is rather limited, we propose to leverage object candidate priors provided in existing image datasets and also correspondence consistency between object pairs to enable weakly-supervised learning. Experiments demonstrate that FCSS outperforms conventional handcrafted descriptors and CNN-based descriptors on various benchmarks.
AB - We present a descriptor, called fully convolutional self-similarity (FCSS), for dense semantic correspondence. To robustly match points among different instances within the same object class, we formulate FCSS using local self-similarity (LSS) within a fully convolutional network. In contrast to existing CNN-based descriptors, FCSS is inherently insensitive to intra-class appearance variations because of its LSS-based structure, while maintaining the precise localization ability of deep neural networks. The sampling patterns of local structure and the self-similarity measure are jointly learned within the proposed network in an end-to-end and multi-scale manner. As training data for semantic correspondence is rather limited, we propose to leverage object candidate priors provided in existing image datasets and also correspondence consistency between object pairs to enable weakly-supervised learning. Experiments demonstrate that FCSS outperforms conventional handcrafted descriptors and CNN-based descriptors on various benchmarks.
UR - http://www.scopus.com/inward/record.url?scp=85041917113&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2017.73
DO - 10.1109/CVPR.2017.73
M3 - Conference contribution
AN - SCOPUS:85041917113
T3 - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
SP - 616
EP - 625
BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 21 July 2017 through 26 July 2017
ER -