Learning Spread-out Local Feature Descriptors
This work addresses the challenge of underutilized descriptor space in computer vision, offering an incremental improvement for tasks like image matching and retrieval.
The paper tackles the problem of learning local feature descriptors by proposing a spread-out regularization technique to maximize descriptor diversity, which significantly improves pairwise and triplet losses and outperforms existing Euclidean distance-based methods by a large margin.
We propose a simple, yet powerful regularization technique that can be used to significantly improve both the pairwise and triplet losses in learning local feature descriptors. The idea is that in order to fully utilize the expressive power of the descriptor space, good local feature descriptors should be sufficiently "spread-out" over the space. In this work, we propose a regularization term to maximize the spread in feature descriptor inspired by the property of uniform distribution. We show that the proposed regularization with triplet loss outperforms existing Euclidean distance based descriptor learning techniques by a large margin. As an extension, the proposed regularization technique can also be used to improve image-level deep feature embedding.