Preprint · 2019 · Open access
Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
arXiv (Cornell University), 32, 1430–1440 · Published 15 September 2019 · DOI 10.48550/arxiv.1909.06720
In brief
“Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution” is a 2019 preprint by Thang Vu and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 157 citations as of 15 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 157
- Most cited in
- 2024 (38)
- References
- 44
- Authors
- 4
Abstract
This paper considers an architecture referred to as Cascade Region Proposal Network (Cascade RPN) for improving the region-proposal quality and detection performance by \textit{systematically} addressing the limitation of the conventional RPN that \textit{heuristically defines} the anchors and \textit{aligns} the features to the anchors. First, instead of using multiple anchors with predefined scales and aspect ratios, Cascade RPN relies on a \textit{single anchor} per location and performs multi-stage refinement. Each stage is progressively more stringent in defining positive samples by starting out with an anchor-free metric followed by anchor-based metrics in the ensuing stages. Second, to attain alignment between the features and the anchors throughout the stages, \textit{adaptive convolution} is proposed that takes the anchors in addition to the image features as its input and learns the sampled features guided by the anchors. A simple implementation of a two-stage Cascade RPN achieves AR 13.4 points higher than that of the conventional RPN, surpassing any existing region proposal methods. When adopting to Fast R-CNN and Faster R-CNN, Cascade RPN can improve the detection mAP by 3.1 and 3.5 points, respectively. The code is made publicly available at \url{https://github.com/thangvubk/Cascade-RPN.git}.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Vu, T., Jang, H., Pham, T. X., & Yoo, C. D. (2019). Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution. arXiv (Cornell University), 32, 1430–1440. https://doi.org/10.48550/arxiv.1909.06720
MLA 9
Vu, Thang, et al. “Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution.” arXiv (Cornell University), vol. 32, 2019, pp. 1430–1440. https://doi.org/10.48550/arxiv.1909.06720.
Chicago
Vu, Thang, Hyunjun Jang, Trung X. Pham, and Chang D. Yoo. 2019. “Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution.” arXiv (Cornell University) 32: 1430–1440. https://doi.org/10.48550/arxiv.1909.06720.
Harvard
Vu, T. et al. (2019) ‘Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution’, arXiv (Cornell University), 32, pp. 1430–1440. doi:10.48550/arxiv.1909.06720.
IEEE
T. Vu, H. Jang, T. X. Pham, and C. D. Yoo, “Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution,” arXiv (Cornell University), vol. 32, pp. 1430–1440, 2019, doi: 10.48550/arxiv.1909.06720.
BibTeX
@misc{vu2019cascade,
title = {{Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution}},
author = {Vu, Thang and Jang, Hyunjun and Pham, Trung X. and Yoo, Chang D.},
howpublished = {arXiv (Cornell University)},
year = {2019},
volume = {32},
pages = {1430--1440},
doi = {10.48550/arxiv.1909.06720},
url = {https://doi.org/10.48550/arxiv.1909.06720}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2020 | 16 | |
| 2021 | 27 | |
| 2022 | 20 | |
| 2023 | 34 | |
| 2024 | 38 | |
| 2025 | 20 | |
| 2026 | 2 |
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- region proposal network
- adaptive convolution
- object detection
- Faster R-CNN
- Fast R-CNN
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Vu, T., Jang, H., Pham, T. X., & Yoo, C. D. (2019). Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution. arXiv (Cornell University), 32, 1430–1440. https://doi.org/10.48550/arxiv.1909.06720
How many times has this paper been cited?
157 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Thang Vu, Hyunjun Jang, Trung X. Pham, Chang D. Yoo.
What is the DOI of this paper?
10.48550/arxiv.1909.06720. The permanent link is https://doi.org/10.48550/arxiv.1909.06720.
Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.