English

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features

Computer Vision and Pattern Recognition 2016-03-03 v1

Abstract

Although recent advances in regional Convolutional Neural Networks (CNNs) enable them to outperform conventional techniques on standard object detection and classification tasks, their response time is still slow for real-time performance. To address this issue, we propose a method for region proposal as an alternative to selective search, which is used in current state-of-the art object detection algorithms. We evaluate our Keypoint Density-based Region Proposal (KDRP) approach and show that it speeds up detection and classification on fine-grained tasks by 100% versus the existing selective search region proposal technique without compromising classification accuracy. KDRP makes the application of CNNs to real-time detection and classification feasible.

Keywords

Cite

@article{arxiv.1603.00502,
  title  = {Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features},
  author = {JT Turner and Kalyan Gupta and Brendan Morris and David W. Aha},
  journal= {arXiv preprint arXiv:1603.00502},
  year   = {2016}
}

Comments

9 pages, 5 figures, 3 tables

R2 v1 2026-06-22T13:01:32.245Z