当前位置: X-MOL 学术IEEE Trans. Cybern. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Error Correcting Input and Output Hashing
IEEE Transactions on Cybernetics ( IF 9.4 ) Pub Date : 1-4-2018 , DOI: 10.1109/tcyb.2017.2785621
Chao Ma , Ivor W. Tsang , Fumin Shen , Chuancai Liu

Most learning-based hashing algorithms leverage sample-to-sample similarities, such as neighborhood structure, to generate binary codes, which achieve promising results for image retrieval. This type of methods are referred to as instance-level encoding. However, it is nontrivial to define a scalar to represent sample-to-sample similarity encoding the semantic labels and the data structure. To address this issue, in this paper, we seek to use a class-level encoding method, which encodes the class-toclass relationship, to take the semantic information of classes into consideration. Based on these two encodings, we propose a novel framework, error correcting input and output (EC-IO) coding, which does class-level and instance-level encoding under a unified mapping space. Our proposed model contains two major components, which are distribution preservation and error correction. With these two components, our model maps the input feature of samples and the output code of classes into a unified space to encode the intrinsic structure of data and semantic information of classes simultaneously. Under this framework, we present our hashing model, EC-IO hashing (EC-IOH), by approximating the mapping space with the Hamming space. Extensive experiments are conducted to evaluate the retrieval performance, and ECIOH exhibits superior and competitive performances comparing with popular supervised and unsupervised hashing methods.

中文翻译:


纠错输入和输出哈希



大多数基于学习的哈希算法利用样本之间的相似性(例如邻域结构)来生成二进制代码,从而为图像检索带来有希望的结果。这种类型的方法称为实例级编码。然而,定义一个标量来表示编码语义标签和数据结构的样本间相似性并不简单。为了解决这个问题,在本文中,我们寻求使用类级编码方法,对类与类之间的关系进行编码,以考虑类的语义信息。基于这两种编码,我们提出了一种新颖的框架,即纠错输入和输出(EC-IO)编码,它在统一的映射空间下进行类级和实例级编码。我们提出的模型包含两个主要组成部分,即分布保持和误差校正。通过这两个组件,我们的模型将样本的输入特征和类的输出代码映射到统一的空间中,以同时编码数据的内在结构和类的语义信息。在此框架下,我们通过用汉明空间近似映射空间来提出我们的哈希模型,EC-IO 哈希(EC-IOH)。进行了大量的实验来评估检索性能,与流行的监督和无监督哈希方法相比,ECIOH 表现出优越且有竞争力的性能。
更新日期:2024-08-22
down
wechat
bug