Iterative Class Prototype Calibration for Transductive Zero-Shot Learning

Hairui Yang, Baoli Sun, Baopu Li, Caifei Yang, Zhihui Wang*, Jenhui Chen, Lei Wang, Haojie Li

*Corresponding author for this work

Research output: Contribution to journalJournal Article peer-review

15 Scopus citations

Abstract

Zero-shot learning (ZSL) typically suffers from the domain shift issue since the projected feature embedding of unseen samples mismatch with the corresponding class semantic prototypes, making it very challenging to fine-tune an optimal visual-semantic mapping for the unseen domain. Some existing transductive ZSL methods solve this problem by introducing unlabeled samples of the unseen domain, in which the projected features of unseen samples are still not discriminative and tend to be distributed around prototypes of seen classes. Therefore, how to effectively align the projection features of samples in unseen classes with corresponding predefined class prototypes is crucial for promoting the generalization of ZSL models. In this paper, we propose a novel Iterative Class Prototype Calibration (ICPC) framework for transductive ZSL which consists of a pseudo-labeling stage and a model retraining stage to address the above key issue. First, in the labeling stage, we devise a Class Prototype Calibration (CPC) module to calibrate the predefined class prototypes of the unseen domain by estimating the real center of projected feature distribution, which achieves better matching of sample points and class prototypes. Next, in the retraining stage, we devise a Certain Samples Screening (CSS) module to select relatively certain unseen samples with high confidence and align them with predefined class prototypes in the embedding space. A progressive training strategy is adopted to select more certain samples and update the proposed model with augmented training data. Extensive experiments on AwA2, CUB, and SUN datasets demonstrate that the proposed scheme achieves new state-of-the-art in the conventional setting under both standard split (SS) and proposed split (PS).

Original languageEnglish
Pages (from-to)1236-1246
Number of pages11
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume33
Issue number3
DOIs
StatePublished - 01 03 2023

Bibliographical note

Publisher Copyright:
© 1991-2012 IEEE.

Keywords

  • Transductive zero-shot learning
  • prototype calibration
  • semantic alignment

Fingerprint

Dive into the research topics of 'Iterative Class Prototype Calibration for Transductive Zero-Shot Learning'. Together they form a unique fingerprint.

Cite this