Transductive Zero-Shot Learning With Adaptive Structural Embedding

Yunlong Yu

doi:10.1109/TNNLS.2017.2753852

Return

Transductive Zero-Shot Learning With Adaptive Structural Embedding

2018-09-01

DOI：10.1109/TNNLS.2017.2753852

Original

Save

View PDF

Abstract

En 中文

Zero-shot learning (ZSL) endows the computer vision system with the inferential capability to recognize new categories that have never seen before. Two fundamental challenges in it are visual-semantic embedding and domain adaptation in crossmodality learning and unseen class prediction steps, respectively. This paper presents two corresponding methods named Adaptive STructural Embedding (ASTE) and Self-PAced Selective Strategy (SPASS) for both challenges. Specifically, ASTE formulates the visual-semantic interactions in a latent structural support vector machine framework by adaptively adjusting the slack variables to embody different reliablenesses among training instances. To alleviate the domain shift problem in ZSL, SPASS borrows the idea from self-paced learning by iteratively selecting the unseen instances from reliable to less reliable to gradually adapt the knowledge from the seen domain to the unseen domain. Consequently, by combining SPASS and ASTE, we present a self-paced Transductive ASTE (TASTE) method to progressively reinforce the classification capacity. Extensive experiments on three benchmark data sets (i.e., AwA, CUB, and aPY) demonstrate the superiorities of ASTE and TASTE. Furthermore, we also propose a fast training (FT) strategy to improve the efficiency of most existing ZSL methods. The FT strategy is surprisingly simple and general enough, which speeds up the training time of most existing ZSL methods by 4 similar to 300 times while holding the previous performance.

Keywords:

Adaptive structural embedding (ASTE)

domain shift

transductive learning

zero-shot learning (ZSL)

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.