Journal
NEUROCOMPUTING
Volume 402, Issue -, Pages 89-99Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2020.03.077
Keywords
Deep hashing; Multi-label image retrieval; Multiple-instance ranking
Categories
Funding
- National Natural Science Foundation of China [61872045]
- Foundation for Innovative Research Groups of the National Natural Science Foundation of China [61921003]
Ask authors/readers for more resources
Hashing methods have been widely applied to approximate nearest neighbor search in large-scale image retrieval due to its fast search speed and efficient storage space. In practice, most images are with multiple category-aware objects, i.e., multi-label images. This paper focuses on hash code learning for multi-label image retrieval. Most existing hashing methods directly extract one patch such as a downsized crop from each image as a training example, which ignores the multi-label characteristic of images and leads to suboptimal representations for multi-label images. Some researches have proved that each multi-label image follows a multi-instance assumption, where each image is represented as a bag of category-aware proposals (instances). However, existing multiple-instance learning methods use predefined statistical functions with limited learning capability to construct bag features, and they are designed for classification or pairwise-similarity preserving. Thus, directly applying existing multiple-instance learning methods into deep hashing framework still leads to suboptimal hash codes for retrieval. In this paper, we pose hashing learning for multi-label image retrieval as a problem of multiple-instance ranking learning. To solve this problem, we present an end-to-end deep hashing framework, referred to as Deep Multiple-Instance Ranking based Hashing (DMIRH). In DMIRH, we design a category-aware bag feature construction module, which jointly assigns the learned instances into categories and aggregates the selected instance features into a bag feature representation that can capture the multi-label information of each image. In addition, we propose a novel learning objective, which consists of an Inner Product distance based quantization loss to control the hash quality and a listwise ranking loss to preserve the ranking relationships. Experimental results on public benchmarks show the superiority of DMIRH over several state-of-the-art hashing methods. (C) 2020 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available