no code implementations • 26 Feb 2021 • Cheng Xie, Ting Zeng, Hongxin Xiang, Keqin Li, Yun Yang, Qing Liu
The approach also applies a semi-supervised learning process to re-train knowledge-to-visual model.
no code implementations • 23 Feb 2021 • Hongxin Xiang, Cheng Xie, Ting Zeng, Yun Yang
Suffering from the semantic insufficiency and domain-shift problems, most of existing state-of-the-art methods fail to achieve satisfactory results for Zero-Shot Learning (ZSL).
no code implementations • 25 Jan 2021 • Cheng Xie, Hongxin Xiang, Ting Zeng, Yun Yang, Beibei Yu, Qing Liu
CKL enables more relevant semantic features to be trained for semantic-to-visual feature embedding in ZSL, while Taxonomy Regularization (TR) significantly improves the intersections with unseen images with more generalized visual features generated from generative network.