Zero shot learning (ZSL) aims to recognize unseen classes by exploiting semantic relationships between seen and unseen classes. Two major problems faced by ZSL algorithms are the hubness problem and the bias towards the seen classes. Existing ZSL methods focus on only one of these problems in the conventional and generalized ZSL setting. In this work, we propose a novel approach, Semantically Aligned Bias Reducing (SABR) ZSL, which focuses on solving both the problems. It overcomes the hubness problem by learning a latent space that preserves the semantic relationship between the labels while encoding the discriminating information about the classes. Further, we also propose ways to reduce the bias of the seen classes through a simple cross-validation process in the inductive setting and a novel weak transfer constraint in the transductive setting. Extensive experiments on three benchmark datasets suggest that the proposed model significantly outperforms existing state-of-the-art algorithms by ~1.5-9% in the conventional ZSL setting and by ~2-14% in the generalized ZSL for both the inductive and transductive settings.

本文提出了一种新的零样本学习方法——Semantically Aligned Bias Reducing (SABR) ZSL，旨在通过学习一个潜在空间来解决hubness问题，同时通过交叉验证和弱转移约束来减轻示例类别偏移问题，并在三个基准数据集上广泛实验证明，与现有的最先进算法相比，在传统和推广的ZSL设置下，性能显著提高了1.5-9％或2-14％。

语义对齐减少偏见的零样本学习