# PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors

arXiv: https://arxiv.org/abs/1601.05030 · HTML: https://mlsanity.com/paper/1601.05030/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jan 2016.

## Built on by (most cited first, 16 of 16)

- [DFM: A Performance Baseline for Deep Feature Matching](https://mlsanity.com/paper/2106.07791/) (2021)
- [SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence](https://mlsanity.com/paper/2209.07806/) (2022)
- [HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences](https://mlsanity.com/paper/2103.15573/) (2021)
- [Sim2Real Object-Centric Keypoint Detection and Description](https://mlsanity.com/paper/2202.00448/) (2022)
- [Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenes](https://mlsanity.com/paper/2109.03585/) (2021)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Visual Correspondence Hallucination](https://mlsanity.com/paper/2106.09711/) (2021)
- [Bias and Fairness in Computer Vision Applications of the Criminal Justice System](https://mlsanity.com/paper/2208.03209/) (2022)
- [Learning multi-domain feature relation for visible and Long-wave Infrared image patch matching](https://mlsanity.com/paper/2308.04880/) (2023)
- [Relational Representation Learning Network for Cross-Spectral Image Patch Matching](https://mlsanity.com/paper/2403.11751/) (2024)
- [Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching](https://mlsanity.com/paper/2412.11161/) (2024)
- [An embedding for EEG signals learned using a triplet loss](https://mlsanity.com/paper/2304.06495/) (2023)
- [Towards the Influence of Text Quantity on Writer Retrieval](https://mlsanity.com/paper/2506.07566/) (2025)
- [Attention-Based Multimodal Image Matching](https://mlsanity.com/paper/2103.11247/) (2021)
- [A Structure Feature Algorithm for Multi-modal Forearm Registration](https://mlsanity.com/paper/2111.05485/) (2021)
- [Multi-Sensor Matching with HyperNetworks](https://mlsanity.com/paper/2601.12325/) (2026)

## Abstract (arXiv)

In this paper we propose a new approach for learning local descriptors for matching image patches. It has recently been demonstrated that descriptors based on convolutional neural networks (CNN) can significantly improve the matching performance. Unfortunately their computational complexity is prohibitive for any practical application. We address this problem and propose a CNN based descriptor with improved matching performance, significantly reduced training and execution time, as well as low dimensionality. We propose to train the network with triplets of patches that include a positive and negative pairs. To that end we introduce a new loss function that exploits the relations within the triplets. We compare our approach to recently introduced MatchNet and DeepCompare and demonstrate the advantages of our descriptor in terms of performance, memory footprint and speed i.e. when run in GPU, the extraction time of our 128 dimensional feature is comparable to the fastest available binary descriptors such as BRIEF and ORB.