TY - GEN
T1 - Image deformation meta-networks for one-shot learning
AU - Chen, Zitian
AU - Fu, Yanwei
AU - Wang, Yu Xiong
AU - Ma, Lin
AU - Liu, Wei
AU - Hebert, Martial
N1 - Funding Information:
This work is supported in part by the grants from NSFC (#61702108)
Funding Information:
Acknowledgment: This work is supported in part by the grantsfromNSFC(#61702108),STCSM(#16JC1420400), EasternScholar(TP2017006), andTheThousandTalents Plan of China (for young professionals, D1410009).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Humans can robustly learn novel visual concepts even when images undergo various deformations and loose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts from one or few examples. Our key insight is that, while the deformed images may not be visually realistic, they still maintain critical semantic information and contribute significantly to formulating classifier decision boundaries. Inspired by the recent progress of meta-learning, we combine a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner. The deformation sub-network learns to deform images by fusing a pair of images-A probe image that keeps the visual content and a gallery image that diversifies the deformations. We demonstrate results on the widely used one-shot learning benchmarks (miniImageNet and ImageNet 1K Challenge datasets), which significantly outperform state-of-the-art approaches.
AB - Humans can robustly learn novel visual concepts even when images undergo various deformations and loose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts from one or few examples. Our key insight is that, while the deformed images may not be visually realistic, they still maintain critical semantic information and contribute significantly to formulating classifier decision boundaries. Inspired by the recent progress of meta-learning, we combine a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner. The deformation sub-network learns to deform images by fusing a pair of images-A probe image that keeps the visual content and a gallery image that diversifies the deformations. We demonstrate results on the widely used one-shot learning benchmarks (miniImageNet and ImageNet 1K Challenge datasets), which significantly outperform state-of-the-art approaches.
KW - Representation Learning
KW - Statistical Learning
UR - http://www.scopus.com/inward/record.url?scp=85075981872&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075981872&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00888
DO - 10.1109/CVPR.2019.00888
M3 - Conference contribution
AN - SCOPUS:85075981872
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 8672
EP - 8681
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Y2 - 16 June 2019 through 20 June 2019
ER -