# Local Feature Extraction from Salient Regions by Feature Map Transformation

arXiv: https://arxiv.org/abs/2301.10413 · HTML: https://mlsanity.com/paper/2301.10413/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 25 Jan 2023.

## Builds on (most cited first, 28 of 28)

- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Large-Scale Image Retrieval with Attentive Deep Local Features](https://mlsanity.com/paper/1612.06321/) (2016)
- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [LF-Net: Learning Local Features from Images](https://mlsanity.com/paper/1805.09662/) (2018)
- [A Closed-form Solution to Photorealistic Image Stylization](https://mlsanity.com/paper/1802.06474/) (2018)
- [ASLFeat: Learning Local Features of Accurate Shape and Localization](https://mlsanity.com/paper/2003.10071/) (2020)
- [Patch2Pix: Epipolar-Guided Pixel-Level Correspondences](https://mlsanity.com/paper/2012.01909/) (2020)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [Switchable Whitening for Deep Representation Learning](https://mlsanity.com/paper/1904.09739/) (2019)
- [Decorrelated Batch Normalization](https://mlsanity.com/paper/1804.08450/) (2018)
- [Unsupervised Domain Adaptation using Feature-Whitening and Consensus Loss](https://mlsanity.com/paper/1903.03215/) (2019)
- [Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation](https://mlsanity.com/paper/1812.09912/) (2018)
- [GIFT: Learning Transformation-Invariant Dense Visual Descriptors via Group CNNs](https://mlsanity.com/paper/1911.05932/) (2019)
- [Local Descriptors Optimized for Average Precision](https://mlsanity.com/paper/1804.05312/) (2018)
- [Online Invariance Selection for Local Feature Descriptors](https://mlsanity.com/paper/2007.08988/) (2020)
- [D2D: Keypoint Extraction with Describe to Detect Approach](https://mlsanity.com/paper/2005.13605/) (2020)
- [Decoupling Makes Weakly Supervised Local Feature Better](https://mlsanity.com/paper/2201.02861/) (2022)
- [Image Stylization for Robust Features](https://mlsanity.com/paper/2008.06959/) (2020)

## Built on by (most cited first, 1 of 1)

- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)

## Abstract (arXiv)

Local feature matching is essential for many applications, such as localization and 3D reconstruction. However, it is challenging to match feature points accurately in various camera viewpoints and illumination conditions. In this paper, we propose a framework that robustly extracts and describes salient local features regardless of changing light and viewpoints. The framework suppresses illumination variations and encourages structural information to ignore the noise from light and to focus on edges. We classify the elements in the feature covariance matrix, an implicit feature map information, into two components. Our model extracts feature points from salient regions leading to reduced incorrect matches. In our experiments, the proposed method achieved higher accuracy than the state-of-the-art methods in the public dataset, such as HPatches, Aachen Day-Night, and ETH, which especially show highly variant viewpoints and illumination.