Bi-directional Distribution Alignment for Transductive Zero-Shot Learning

Zhicai Wang, Yanbin Hao, Tingting Mu, Ouxiang Li, Shuo Wang, Xiangnan He

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Zero-shot learning (ZSL) suffers intensely from the domain shift issue, i.e., the mismatch (or misalignment) between the true and learned data distributions for classes without training data (unseen classes). By learning additionally from unlabelled data collected for the unseen classes, transductive ZSL (TZSL) could reduce the shift but only to a certain extent. To improve TZSL, we propose a novel approach Bi-VAEGAN which strengthens the distribution alignment between the visual space and an auxiliary space. As a result, it can reduce largely the domain shift. The proposed key designs include (1) a bi-directional distribution alignment, (2) a simple but effective L2-norm based feature normalization approach, and (3) a more sophisticated unseen class prior estimation. Evaluated by four benchmark datasets, Bi-VAEGAN1 achieves the new state of the art under both the standard and generalized TZSL settings.
Original languageEnglish
Title of host publicationIEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR)
Publication statusAccepted/In press - 27 Feb 2023


Dive into the research topics of 'Bi-directional Distribution Alignment for Transductive Zero-Shot Learning'. Together they form a unique fingerprint.

Cite this