.png){kind=icon}
返回
Context-aware deep kernel networks for image annotation
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2021.12.006.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Context plays a crucial role in visual recognition as it provides complementary clues for different learning tasks including image classification and annotation. As the performances of these tasks are currently reaching a plateau, any extra knowledge, including context, should be leveraged in ordficant leaps in these performances. In the particular scenario of kernel machines, context-aware kernel design aims at learning positive semi-definite similarity functions which return high values not only when data share similar contents, but also similar structures (a.k.a. contexts). However, the use of context in kernel design has not been fully explored; indeed, context in these solutions is handcrafted instead of being learned. In this paper, we introduce a novel deep network architecture that learns context in kernel design. This architecture is fully determined by the solution of an objective function mixing a content term that cap-tures the intrinsic similarity between data, a context criterion which models their structure and a regu-larization term that helps designing smooth kernel network representations. The solution of this objective function defines a particular deep network architecture whose parameters correspond to differ-ent variants of learned contexts including layerwise, stationary and classwise; larger values of these parameters correspond to the most influencing contextual relationships between data. Extensive exper-iments conducted on the challenging ImageCLEF Photo Annotation, Corel5k and NUS-WIDE benchmarks show that our deep context networks are highly effective for image classification and the learned con-texts further enhance the performance of image annotation. (c) 2021 Elsevier B.V. All rights reserved.
Keyword:
Deep kernel learning
Context-aware kernel networks
Deep learning
Image annotation
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
分享收藏Solution Structure of Monomeric Peptide YY Supports the Functional Significance of the PP-Fold,.png)
Biochemistry
BiochemistryIF0
PREAI
分享收藏分享收藏
查看更多内容