Book chapter
A Simple and Effective Framework for Pairwise Deep Metric Learning
Computer Vision – ECCV 2020, pp.375-391
Lecture Notes in Computer Science, Springer International Publishing
11/19/2020
DOI: 10.1007/978-3-030-58583-9_23
Abstract
Deep metric learning (DML) has received much attention in deep learning due to its wide applications in computer vision. Previous studies have focused on designing complicated losses and hard example mining methods, which are mostly heuristic and lack of theoretical understanding. In this paper, we cast DML as a simple pairwise binary classification problem that classifies a pair of examples as similar or dissimilar. It identifies the most critical issue in this problem—imbalanced data pairs. To tackle this issue, we propose a simple and effective framework to sample pairs in a batch of data for updating the model. The key to this framework is to define a robust loss for all pairs over a mini-batch of data, which is formulated by distributionally robust optimization. The flexibility in constructing the uncertainty decision set of the dual variable allows us to recover state-of-the-art complicated losses and also to induce novel variants. Empirical studies on several benchmark data sets demonstrate that our simple and effective method outperforms the state-of-the-art results.
Details
- Title: Subtitle
- A Simple and Effective Framework for Pairwise Deep Metric Learning
- Creators
- Qi Qi - University of IowaYan Yan - University of IowaZixuan Wu - Boston CollegeXiaoyu Wang - Chinese University of Hong KongTianbao Yang - University of Iowa
- Resource Type
- Book chapter
- Publication Details
- Computer Vision – ECCV 2020, pp.375-391
- Publisher
- Springer International Publishing; Cham
- Series
- Lecture Notes in Computer Science
- DOI
- 10.1007/978-3-030-58583-9_23
- eISSN
- 1611-3349
- ISSN
- 0302-9743
- Language
- English
- Date published
- 11/19/2020
- Academic Unit
- Computer Science
- Record Identifier
- 9984259498602771
Metrics
52 Record Views