Abstract
In most recent years, zero-shot recognition (ZSR) has gained increasing attention in machine learning and image processing fields. It aims at recognizing unseen class instances with knowledge transferred from seen classes. This is typically achieved by exploiting a pre-defined semantic feature space (FS), i.e., semantic attributes or word vectors, as a bridge to transfer knowledge between seen and unseen classes. However, due to the absence of unseen classes during training, the conventional ZSR easily suffers from domain shift and hubness problems. In this paper, we propose a novel ZSR learning framework that can handle these two issues well by adaptively adjusting semantic FS. To the best of our knowledge, our work is the first to consider the adaptive adjustment of semantic FS in ZSR. Moreover, our solution can be formulated to a more efficient framework that significantly boosts the training. Extensive experiments show the remarkable performance improvement of our model compared with other existing methods.
Abstract (translated)
近几年来,零镜头识别在机器学习和图像处理领域得到了越来越多的关注。它的目的是通过从所见类转移的知识来识别看不见的类实例。这通常是通过利用预先定义的语义特征空间(fs),即语义属性或词向量,作为在可见类和未可见类之间传递知识的桥梁来实现的。然而,由于在训练过程中没有看不见的课程,传统的zsr容易出现域移位和色调问题。本文提出了一种新的zsr学习框架,通过自适应调整语义fs,可以很好地解决这两个问题。据我们所知,我们的工作首先考虑了zsr中语义fs的自适应调整。此外,我们的解决方案可以制定成一个更有效的框架,大大促进培训。大量实验表明,与现有方法相比,该模型的性能有了显著的提高。
URL
https://arxiv.org/abs/1904.00170