Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Manifold and patch-based unsupervised deep metric learning for fine-grained image retrieval: Manifold and patch-based unsupervised deep metric learning for fine-grained image retrieval: S. Yuan et al. |
| Συγγραφείς: |
Yuan, Shi-hao, Feng, Yong, Qiu, A-Gen, Duan, Guo-fan, Zhou, Ming-liang, Qiang, Bao-hua, Wang, Yong-heng |
| Πηγή: |
Applied Intelligence; Jan2025, Vol. 55 Issue 2, p1-18, 18p |
| Θεματικοί όροι: |
Deep learning, Image retrieval, Artificial intelligence, Cognitive psychology, Image processing |
| Περίληψη: |
Accurately and swiftly retrieving from fine-grained images is a critical and challenging task. As the key technology for fine-grained image retrieval, deep metric learning aims to learn a mapping space, where samples exhibit two properties: positive concentration and negative separation, facilitating the measurement of similarities between samples. Unsupervised deep metric learning, which obviates the need for labels during training, has garnered widespread attention compared to its supervised counterparts due to its convenience. Current methods in unsupervised deep metric learning face issues such as imbalance in sample construction, difficulty in sample differentiation, and neglect of intrinsic image features. To address these challenges, we propose Manifold and Patch-based Unsupervised Deep Metric Learning (MPUDML) for Fine-Grained Image Retrieval. Specifically, we adopt a manifold similarity-based balanced sampling strategy for constructing more balanced mini-batch samples. Moreover, we leverage soft supervision information obtained from the manifold and cosine similarities between unlabeled images for sample differentiation, effectively reducing the impact of noisy samples. Additionally, we utilize the rich feature information between internal image patches through image patch-level clustering and localization tasks to guide the acquisition of a more comprehensive feature embedding representation, thereby enhancing retrieval performance. Our method, MPUDML, was evaluated against various state-of-the-art unsupervised deep metric learning approaches in fine-grained image retrieval and clustering tasks. Experimental findings indicate that our MPUDML method exceeds other advanced methods in recall (R@K) and Normalized Mutual Information (NMI). [ABSTRACT FROM AUTHOR] |
|
Copyright of Applied Intelligence is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Βάση Δεδομένων: |
Complementary Index |