End-to-end metric learning from corrupted images using triplet dimensionality reduction loss
- Authors
- Park, Juhyeon; Hong, Jin; Kwon, Junseok
- Issue Date
- Mar-2024
- Publisher
- Elsevier Ltd
- Keywords
- Corrupted images; End-to-end metric learning; Principal component analysis; Triplet dimensionality reduction loss
- Citation
- Expert Systems with Applications, v.238
- Journal Title
- Expert Systems with Applications
- Volume
- 238
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/68600
- DOI
- 10.1016/j.eswa.2023.122064
- ISSN
- 0957-4174
1873-6793
- Abstract
- In this paper, we present a novel dimensionality reduction term (i.e. TripletPCA and ContrastivePCA) designed to enhance the robustness of pair-based loss functions in metric learning against image corruptions. Notably, our approach achieves this without the need for any data preprocessing steps. Our method can be seamlessly integrated into existing models, such as a block with Plug & Play framework. To the best of our knowledge, our TripletPCA and ContrastivePCA represent the first attempts to incorporate dimensionality reduction directly into pair-based metric learning losses for end-to-end metric learning. By projecting image features into low-dimensional vectors, our proposed loss functions effectively retain the essential components of images while mitigating the impact of corrupted features. Consequently, our metric learning loss function accurately computes feature distances through the projection. Experimental results demonstrate that our dimensionality reduction term can be easily incorporated into various types of existing deep neural networks. This integration leads to a substantial improvement in performance on standard benchmark datasets for corrupted image classification tasks. On several corruption datasets, we achieve an average performance improvement of 10.55% compared to existing baseline methods. Our code is available at https://github.com/Juryun/TDRL. © 2023 Elsevier Ltd
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > School of Computer Science and Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.