Open AccessUnbiased hybrid generation network for zero‐shot learning
Author(s) -
Wang ZongHui,
Lu ZiQian,
Lu ZheMing
Publication year - 2020
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2020.1594
Subject(s) - decision boundary , computer science , confusion , artificial intelligence , feature (linguistics) , shot (pellet) , task (project management) , machine learning , zero (linguistics) , semantics (computer science) , boundary (topology) , pattern recognition (psychology) , support vector machine , mathematics , engineering , psychology , mathematical analysis , linguistics , philosophy , chemistry , organic chemistry , systems engineering , psychoanalysis , programming language
While promising progress has been achieved in the zero‐shot learning (ZSL) task. The existing approaches still suffer from the strong bias problem between the unseen and seen classes. This Letter presents a unified feature generating framework equipped with a boundary decision loss to tackle this issue in ZSL. Specifically, the hybrid semantic and visual classification strategy is proposed, which can effectively align the bidirectional visual‐semantic interactions. Furthermore, this Letter introduces a decision loss that optimises the decision boundary of seen and unseen classes to further alleviate the confusion of generated features. Extensive experiments on three popular datasets animals with attributes, Caltech‐UCSD‐Birds 200‐2011, and SUN show that the proposed approach outperforms previous state‐of‐the‐art works under both traditional ZSL and challenging generalised ZSL settings.