Skip to main content

Research Repository

Advanced Search

HSE: Hybrid Species Embedding for Deep Metric Learning

Yang, Bailin; Sun, Haoqiang; Li, Frederick W. B.; Chen, Zheng; Cai, Jianlu; Song, Chao

HSE: Hybrid Species Embedding for Deep Metric Learning Thumbnail


Authors

Bailin Yang

Haoqiang Sun

Zheng Chen

Jianlu Cai

Chao Song



Abstract

Deep metric learning is crucial for finding an embedding function that can generalize to training and testing data, including unknown test classes. However, limited training samples restrict the model's generalization to downstream tasks. While adding new training samples is a promising solution, determining their labels remains a significant challenge. Here, we introduce Hybrid Species Embedding (HSE), which employs mixed sample data augmentations to generate hybrid species and provide additional training signals. We demonstrate that HSE outperforms multiple state-of-the-art methods in improving the metric Recall@K on the CUB-200 , CAR-196 and SOP datasets, thus offering a novel solution to deep metric learning's limitations.

Citation

Yang, B., Sun, H., Li, F. W. B., Chen, Z., Cai, J., & Song, C. (2024). HSE: Hybrid Species Embedding for Deep Metric Learning. In 2023 IEEE/CVF International Conference on Computer Vision (ICCV). https://doi.org/10.1109/ICCV51070.2023.01014

Presentation Conference Type Conference Paper (Published)
Conference Name 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Start Date Oct 2, 2023
End Date Oct 6, 2023
Acceptance Date Aug 11, 2023
Online Publication Date Jan 15, 2024
Publication Date Jan 15, 2024
Deposit Date Sep 12, 2023
Publicly Available Date Jan 15, 2024
Publisher Institute of Electrical and Electronics Engineers
Series ISSN 1550-5499
Book Title 2023 IEEE/CVF International Conference on Computer Vision (ICCV)
ISBN 9798350307191
DOI https://doi.org/10.1109/ICCV51070.2023.01014
Public URL https://durham-repository.worktribe.com/output/1735635

Files





You might also like



Downloadable Citations