Chrome Extension
WeChat Mini Program
Use on ChatGLM

Learning-Based Dimensionality Reduction for Computing Compact and Effective Local Feature Descriptors

2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA(2023)

Cited 2|Views36
No score
Abstract
A distinctive representation of image patches in form of features is a key component of many computer vision and robotics tasks, such as image matching, image retrieval, and visual localization. State-of-the-art descriptors, from handcrafted descriptors such as SIFT to learned ones such as HardNet, are usually high-dimensional; 128 dimensions or even more. The higher the dimensionality, the larger the memory consumption and computational time for approaches using such descriptors. In this paper, we investigate multi-layer perceptrons (MLPs) to extract low-dimensional but high-quality descriptors. We thoroughly analyze our method in unsupervised, self-supervised, and supervised settings, and evaluate the dimensionality reduction results on four representative descriptors. We consider different applications, including visual localization, patch verification, image matching and retrieval. The experiments show that our lightweight MLPs trained using supervised method achieve better dimensionality reduction than PCA. The lower-dimensional descriptors generated by our approach outperform the original higher-dimensional descriptors in downstream tasks, especially for the hand-crafted ones. The code is available at https://github.com/PRBonn/descriptor-dr.
More
Translated text
Key words
computational time,computer vision,dimensionality reduction results,distinctive representation,effective local feature descriptors,hand-crafted descriptors,hand-crafted ones,high-quality descriptors,higher-dimensional descriptors,image matching,image patches,image retrieval,learned ones,lower-dimensional descriptors,memory consumption,multilayer perceptrons to extract low-dimensional,patch verification,representative descriptors,robotics tasks,state-of-the-art descriptors,supervised method,supervised settings,visual localization
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined