# Fracking Deep Convolutional Image Descriptors

arXiv: https://arxiv.org/abs/1412.6537 · HTML: https://mlsanity.com/paper/1412.6537/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2014.

## Built on by (most cited first, 7 of 7)

- [Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2108.04547/) (2021)
- [Close, But Not There: Boosting Geographic Distance Sensitivity in Visual Place Recognition](https://mlsanity.com/paper/2407.02422/) (2024)
- [Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks](https://mlsanity.com/paper/2311.01038/) (2023)
- [Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning](https://mlsanity.com/paper/2309.03598/) (2023)
- [Does Interference Exist When Training a Once-For-All Network?](https://mlsanity.com/paper/2204.09210/) (2022)
- [A Triplet-loss Dilated Residual Network for High-Resolution Representation Learning in Image Retrieval](https://mlsanity.com/paper/2303.08398/) (2023)
- [On the Importance of Large Objects in CNN Based Object Detection Algorithms](https://mlsanity.com/paper/2311.11714/) (2023)

## Abstract (arXiv)

In this paper we propose a novel framework for learning local image descriptors in a discriminative manner. For this purpose we explore a siamese architecture of Deep Convolutional Neural Networks (CNN), with a Hinge embedding loss on the L2 distance between descriptors. Since a siamese architecture uses pairs rather than single image patches to train, there exist a large number of positive samples and an exponential number of negative samples. We propose to explore this space with a stochastic sampling of the training set, in combination with an aggressive mining strategy over both the positive and negative samples which we denote as "fracking". We perform a thorough evaluation of the architecture hyper-parameters, and demonstrate large performance gains compared to both standard CNN learning strategies, hand-crafted image descriptors like SIFT, and the state-of-the-art on learned descriptors: up to 2.5x vs SIFT and 1.5x vs the state-of-the-art in terms of the area under the curve (AUC) of the Precision-Recall curve.