TY - GEN
T1 - MATGAN
T2 - 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2022
AU - Guo, Xi
AU - Rao, Qiang
AU - He, Kun
AU - Chen, Fang
AU - Yu, Bing
AU - Feng, Bailan
AU - Huang, Jian
AU - Yang, Qin
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Image attribute transfer aims to change an image to a target one with desired attributes. There are mainly two challenges for this task: multi-domain transfer and attribute-level multimodality. The first means editing multiple attributes using a single model and the second means diverse appearances for the target attribute. Existing methods cannot address the two problems simultaneously. Moreover, many works focus on image-level multimodality rather than attribute-level. In this paper, we propose a novel coarse-to-fine disentangling representation framework MATGAN to achieve Multimodal Attribute Transfer. In the coarse disentangling stage, we propose to embed images onto a content space and an attribute space for image-level multimodality. In the fine disentangling stage, we further disentangle the attribute space to bind with each attribute for attribute-level multimodal and multi-domain transfer. Extensive experiments demonstrate the effectiveness of our approach.
AB - Image attribute transfer aims to change an image to a target one with desired attributes. There are mainly two challenges for this task: multi-domain transfer and attribute-level multimodality. The first means editing multiple attributes using a single model and the second means diverse appearances for the target attribute. Existing methods cannot address the two problems simultaneously. Moreover, many works focus on image-level multimodality rather than attribute-level. In this paper, we propose a novel coarse-to-fine disentangling representation framework MATGAN to achieve Multimodal Attribute Transfer. In the coarse disentangling stage, we propose to embed images onto a content space and an attribute space for image-level multimodality. In the fine disentangling stage, we further disentangle the attribute space to bind with each attribute for attribute-level multimodal and multi-domain transfer. Extensive experiments demonstrate the effectiveness of our approach.
KW - disentangling representations
KW - generative adversarial networks
KW - multimodal attribute transfer
UR - https://www.scopus.com/pages/publications/85144606634
U2 - 10.1109/FAIML57028.2022.00030
DO - 10.1109/FAIML57028.2022.00030
M3 - 会议稿件
AN - SCOPUS:85144606634
T3 - Proceedings - 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2022
SP - 109
EP - 119
BT - Proceedings - 2022 International Conference on Frontiers of Artificial Intelligence and Machine Learning, FAIML 2022
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 July 2022 through 21 July 2022
ER -