# Quad-networks: unsupervised learning to rank for interest point detection

arXiv: https://arxiv.org/abs/1611.07571 · HTML: https://mlsanity.com/paper/1611.07571/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2016.

## Built on by (most cited first, 30 of 36)

- [Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed](https://mlsanity.com/paper/2403.04765/) (2024)
- [TransVPR: Transformer-based place recognition with multi-level attention aggregation](https://mlsanity.com/paper/2201.02001/) (2022)
- [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021)
- [P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching](https://mlsanity.com/paper/2103.01055/) (2021)
- [MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training](https://mlsanity.com/paper/2501.07556/) (2025)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [Learning Camera Localization via Dense Scene Matching](https://mlsanity.com/paper/2103.16792/) (2021)
- [Decoupling Makes Weakly Supervised Local Feature Better](https://mlsanity.com/paper/2201.02861/) (2022)
- [Self-Supervised Equivariant Learning for Oriented Keypoint Detection](https://mlsanity.com/paper/2204.08613/) (2022)
- [Partially Does It: Towards Scene-Level FG-SBIR with Partial Input](https://mlsanity.com/paper/2203.14804/) (2022)
- [ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement](https://mlsanity.com/paper/2209.12213/) (2022)
- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [Deep Learning for Visual Localization and Mapping: A Survey](https://mlsanity.com/paper/2308.14039/) (2023)
- [S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction](https://mlsanity.com/paper/2308.14598/) (2023)
- [Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network](https://mlsanity.com/paper/2111.09006/) (2021)
- [Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes](https://mlsanity.com/paper/2109.03585/) (2021)
- [A Critical Analysis of Image-based Camera Pose Estimation Techniques](https://mlsanity.com/paper/2201.05816/) (2022)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [SuperPoint features in endoscopy](https://mlsanity.com/paper/2203.04302/) (2022)
- [MD-Net: Multi-Detector for Local Feature Extraction](https://mlsanity.com/paper/2208.05350/) (2022)
- [Shared Coupling-bridge for Weakly Supervised Local Feature Learning](https://mlsanity.com/paper/2212.07047/) (2022)
- [Digging Into Self-Supervised Learning of Feature Descriptors](https://mlsanity.com/paper/2110.04773/) (2021)
- [Learning multi-domain feature relation for visible and Long-wave Infrared image patch matching](https://mlsanity.com/paper/2308.04880/) (2023)
- [Image Feature Information Extraction for Interest Point Detection: A Review](https://mlsanity.com/paper/2106.07929/) (2021)
- [Learning to Detect Good Keypoints to Match Non-Rigid Objects in RGB Images](https://mlsanity.com/paper/2212.09589/) (2022)
- [Scale-Free Image Keypoints Using Differentiable Persistent Homology](https://mlsanity.com/paper/2406.01315/) (2024)
- [CNSv2: Probabilistic Correspondence Encoded Neural Image Servo](https://mlsanity.com/paper/2503.00132/) (2025)
- [Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching](https://mlsanity.com/paper/2112.10485/) (2021)
- [Improving the matching of deformable objects by learning to detect keypoints](https://mlsanity.com/paper/2309.00434/) (2023)
- [HCPM: Hierarchical Candidates Pruning for Efficient Detector-Free Matching](https://mlsanity.com/paper/2403.12543/) (2024)

## Abstract (arXiv)

Several machine learning tasks require to represent the data using only a sparse set of interest points. An ideal detector is able to find the corresponding interest points even if the data undergo a transformation typical for a given domain. Since the task is of high practical interest in computer vision, many hand-crafted solutions were proposed. In this paper, we ask a fundamental question: can we learn such detectors from scratch? Since it is often unclear what points are "interesting", human labelling cannot be used to find a truly unbiased solution. Therefore, the task requires an unsupervised formulation. We are the first to propose such a formulation: training a neural network to rank points in a transformation-invariant manner. Interest points are then extracted from the top/bottom quantiles of this ranking. We validate our approach on two tasks: standard RGB image interest point detection and challenging cross-modal interest point detection between RGB and depth images. We quantitatively show that our unsupervised method performs better or on-par with baselines.