期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 30, 期 -, 页码 2207-2219出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2021.3050677
关键词
Semantics; Visualization; Training; Learning systems; Correlation; Task analysis; Laplace equations; Zero-shot learning; semi-supervised; low-rank semantic grouping; label propagation
资金
- National Natural Science Foundation of China [U1913602, 61936004, 61876219]
- Innovation Group Project of the National Natural Science Foundation of China [61821003]
- Technology Innovation Project of Hubei Province of China [2019AEA171]
- Foundation for Innovative Research Groups of Hubei Province of China [2017CFA005]
- 111 Project on Computational Intelligence and Intelligent Control [B18024]
Zero-shot learning aims to classify new classes based on a model learned from observed classes. This study proposes a Low-rank Semantics Grouping method for semi-supervised zero-shot learning, which has been shown to be efficient on various standard benchmarks.
Zero-shot learning has received great interest in visual recognition community. It aims to classify new unobserved classes based on the model learned from observed classes. Most zero-shot learning methods require pre-provided semantic attributes as the mid-level information to discover the intrinsic relationship between observed and unobserved categories. However, it is impractical to annotate the enriched label information of the observed objects in real-world applications, which would extremely hurt the performance of zero-shot learning with limited labeled seen data. To overcome this obstacle, we develop a Low-rank Semantics Grouping (LSG) method for zero-shot learning in a semi-supervised fashion, which attempts to jointly uncover the intrinsic relationship across visual and semantic information and recover the missing label information from seen classes. Specifically, the visual-semantic encoder is utilized as projection model, low-rank semantic grouping scheme is explored to capture the intrinsic attributes correlations and a Laplacian graph is constructed from the visual features to guide the label propagation from labeled instances to unlabeled ones. Experiments have been conducted on several standard zero-shot learning benchmarks, which demonstrate the efficiency of the proposed method by comparing with state-of-the-art methods. Our model is robust to different levels of missing label settings. Also visualized results prove that the LSG can distinguish the test unseen classes more discriminative.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据