In this paper, we explore how three related tasks, namely keypoint detection, description, and image retrieval can be jointly tackled using a single unified framework, which is trained without the need of training data with point to point correspondences. By leveraging diverse information from sequential layers of a standard ResNet-based architecture, we are able to extract keypoints and descriptors that encode local information using generic techniques such as local activation norms, channel grouping and dropping, and self-distillation. Subsequently, global information for image retrieval is encoded in an end-to-end pipeline, based on pooling of the aforementioned local responses. In contrast to previous methods in local matching, our method does not depend on pointwise/pixelwise correspondences, and requires no such supervision at all i.e. no depth-maps from an SfM model nor manually created synthetic affine transformations. We illustrate that this simple and direct paradigm, is able to achieve very competitive results against the state-of-the-art methods in various challenging benchmark conditions such as viewpoint changes, scale changes, and day-night shifting localization.
@article{arxiv.2001.07252,
title = {UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision},
author = {Tsun-Yi Yang and Duy-Kien Nguyen and Huub Heijnen and Vassileios Balntas},
journal= {arXiv preprint arXiv:2001.07252},
year = {2020}
}