Probabilistic Principal Geodesic Deep Metric Learning

• Published in: IEEE Access
• Main Authors: Dae Ha Kim, Byung Cheol Song
• Format: Article in Journal/Newspaper
• Language: English
• Published: IEEE 2022
• Subjects: Deep metric learning; image retrieval; Stiefel manifold; non-linear mapping; Electrical engineering. Electronics. Nuclear engineering; TK1-9971; DML
• Online Access: https://doi.org/10.1109/ACCESS.2022.3143129; https://doaj.org/article/88bc23efd1e640f2affb6f0acaa11c37

Similarity learning which is useful for the purpose of comparing various characteristics of images in the computer vision field has been often applied for deep metric learning (DML). Also, a lot of combinations of pairwise similarity metrics such as Euclidean distance and cosine similarity have been studied actively. However, such a local similarity-based approach can be rather a bottleneck for a retrieval task in which global characteristics of images must be considered important. Therefore, this paper proposes a new similarity metric structure that considers the local similarity as well as the global characteristic on the representation space, i.e., class variability. Also, based on an insight that better class variability analysis can be accomplished on the Stiefel (or Riemannian) manifold, manifold geometry is employed to generate class variability information. Finally, we show that the proposed method designed through in-depth analysis of generalization bound of DML outperforms conventional DML methods theoretically and experimentally.