# UR2KiD: Unifying Retrieval, Keypoint Detection, and Keypoint Description without Local Correspondence Supervision

arXiv: https://arxiv.org/abs/2001.07252 · HTML: https://mlsanity.com/paper/2001.07252/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jan 2020.

## Built on by (most cited first, 17 of 17)

- [Back to the Feature: Learning Robust Camera Localization from Pixels to Pose](https://mlsanity.com/paper/2103.09213/) (2021)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [EndoMapper dataset of complete calibrated endoscopy procedures](https://mlsanity.com/paper/2204.14240/) (2022)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [Wide-Baseline Multi-Camera Calibration using Person Re-Identification](https://mlsanity.com/paper/2104.08568/) (2021)
- [Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization](https://mlsanity.com/paper/2202.01821/) (2022)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [Multi-Person 3D Pose Estimation from Multi-View Uncalibrated Depth Cameras](https://mlsanity.com/paper/2401.15616/) (2024)
- [A Detector-oblivious Multi-arm Network for Keypoint Matching](https://mlsanity.com/paper/2104.00947/) (2021)
- [Digging Into Self-Supervised Learning of Feature Descriptors](https://mlsanity.com/paper/2110.04773/) (2021)
- [Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression](https://mlsanity.com/paper/2208.00919/) (2022)
- [Reuse your features: unifying retrieval and feature-metric alignment](https://mlsanity.com/paper/2204.06292/) (2022)
- [Soft Expectation and Deep Maximization for Image Feature Detection](https://mlsanity.com/paper/2104.10291/) (2021)
- [CNN-based local features for navigation near an asteroid](https://mlsanity.com/paper/2309.11156/) (2023)
- [TP3M: Transformer-based Pseudo 3D Image Matching with Reference Image](https://mlsanity.com/paper/2405.08434/) (2024)

## Abstract (arXiv)

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.