Piecewise-Linear Manifolds for Deep Metric Learning
This work addresses the challenge of learning semantic representations from unlabeled data for tasks like image retrieval, representing an incremental improvement over current state-of-the-art techniques.
The paper tackles the problem of unsupervised deep metric learning by modeling the data manifold with a piecewise-linear approximation to estimate similarity between data points, resulting in better correlation with ground truth and outperforming existing methods on standard zero-shot image retrieval benchmarks.
Unsupervised deep metric learning (UDML) focuses on learning a semantic representation space using only unlabeled data. This challenging problem requires accurately estimating the similarity between data points, which is used to supervise a deep network. For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point. These neighborhoods are used to estimate similarity between data points. We empirically show that this similarity estimate correlates better with the ground truth than the similarity estimates of current state-of-the-art techniques. We also show that proxies, commonly used in supervised metric learning, can be used to model the piecewise-linear manifold in an unsupervised setting, helping improve performance. Our method outperforms existing unsupervised metric learning approaches on standard zero-shot image retrieval benchmarks.