Transductive Zero-Shot Learning With a Self-Training Dictionary Approach
Transductive Zero-Shot Learning With a Self-Training Dictionary Approach
复制标题
采用自训练字典方法的转导式零样本学习
DOI：
10.1109/tcyb.2017.2751741
复制
发表时间：
2018
影响因子：
11.8
通讯作者：
Li X
中科院分区：
文献类型：
--
作者：
Yu Yunlong;Ji Zhong;Guo Jichang;Li Xi;Wu Fei;Zhang Zhongfei;Zhang Zhongfei;Ling Haibin;Li X
作为计算机视觉领域的一个重要且具有挑战性的问题，零次学习（zero-shot learning，简称ZRL）的目标是在没有训练数据的情况下，从未知对象类中自动识别实例。为了解决这一问题，通常从以下两个方面来进行语义标注：1）捕获可见类数据和不可见类数据之间的域分布连接; 2）对图像特征空间和标签嵌入空间之间的语义交互进行建模。出于这些观察，我们提出了一个双向映射为基础的语义关系建模方案，寻求跨模态的知识转移，同时投影到一个共同的潜在空间的图像特征和标签嵌入。即，我们具有从图像特征空间到潜在空间以及从标签嵌入空间到潜在空间的双向连接关系。为了处理域转移问题，我们进一步提出了一种转导学习方法，该方法在迭代精炼过程中制定类预测问题，其中对象分类能力通过基于引导的模型更新高度可靠的实例逐步加强。在4个基准数据集（animal with attribute，Caltech-UCSD Bird 2011，aPascal-aYahoo，SUN）上的实验结果证明了该方法的有效性。
As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data. To address this problem, ZSL is usually carried out in the following two aspects: 1) capturing the domain distribution connections between seen classes data and unseen classes data and 2) modeling the semantic interactions between the image feature space and the label embedding space. Motivated by these observations, we propose a bidirectional mapping-based semantic relationship modeling scheme that seeks for cross-modal knowledge transfer by simultaneously projecting the image features and label embeddings into a common latent space. Namely, we have a bidirectional connection relationship that takes place from the image feature space to the latent space as well as from the label embedding space to the latent space. To deal with the domain shift problem, we further present a transductive learning approach that formulates the class prediction problem in an iterative refining process, where the object classification capacity is progressively reinforced through bootstrapping-based model updating over highly reliable instances. Experimental results on four benchmark datasets (animal with attribute, Caltech-UCSD Bird2011, aPascal-aYahoo, and SUN) demonstrate the effectiveness of the proposed approach against the state-of-the-art approaches.