Preprint · 2017 · Open access

Zoom Out-and-In Network with Recursive Training for Object Proposal

Hongyang Li, Yu Liu, Wanli Ouyang, Xiaogang Wang

arXiv (Cornell University) · Published 19 February 2017 · DOI 10.48550/arxiv.1702.05711

Open PDFView at the publisherCite this paper

In brief

“Zoom Out-and-In Network with Recursive Training for Object Proposal” is a 2017 preprint by Hongyang Li and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 26 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
26
Most cited in
2017 (5)
References
47
Authors
4

Abstract

In this paper, we propose a zoom-out-and-in network for generating object proposals. We utilize different resolutions of feature maps in the network to detect object instances of various sizes. Specifically, we divide the anchor candidates into three clusters based on the scale size and place them on feature maps of distinct strides to detect small, medium and large objects, respectively. Deeper feature maps contain region-level semantics which can help shallow counterparts to identify small objects. Therefore we design a zoom-in sub-network to increase the resolution of high level features via a deconvolution operation. The high-level features with high resolution are then combined and merged with low-level features to detect objects. Furthermore, we devise a recursive training pipeline to consecutively regress region proposals at the training stage in order to match the iterative regression at the testing stage. We demonstrate the effectiveness of the proposed method on ILSVRC DET and MS COCO datasets, where our algorithm performs better than the state-of-the-arts in various evaluation metrics. It also increases average precision by around 2% in the detection system.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, H., Liu, Y., Ouyang, W., & Wang, X. (2017). Zoom Out-and-In Network with Recursive Training for Object Proposal. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1702.05711

MLA 9

Li, Hongyang, et al. “Zoom Out-and-In Network with Recursive Training for Object Proposal.” arXiv (Cornell University), 2017. https://doi.org/10.48550/arxiv.1702.05711.

Chicago

Li, Hongyang, Yu Liu, Wanli Ouyang, and Xiaogang Wang. 2017. “Zoom Out-and-In Network with Recursive Training for Object Proposal.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.1702.05711.

Harvard

Li, H. et al. (2017) ‘Zoom Out-and-In Network with Recursive Training for Object Proposal’, arXiv (Cornell University). doi:10.48550/arxiv.1702.05711.

IEEE

H. Li, Y. Liu, W. Ouyang, and X. Wang, “Zoom Out-and-In Network with Recursive Training for Object Proposal,” arXiv (Cornell University), 2017, doi: 10.48550/arxiv.1702.05711.

BibTeX

@misc{li2017zoom,
  title     = {{Zoom Out-and-In Network with Recursive Training for Object Proposal}},
  author    = {Li, Hongyang and Liu, Yu and Ouyang, Wanli and Wang, Xiaogang},
  howpublished = {arXiv (Cornell University)},
  year      = {2017},
  doi       = {10.48550/arxiv.1702.05711},
  url       = {https://doi.org/10.48550/arxiv.1702.05711}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
201755
201844
201944
202055
202155
202322
202511

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • object proposal generation
  • multi-scale feature maps
  • deconvolution
  • feature fusion
  • recursive training
  • small object detection
  • object detection

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, H., Liu, Y., Ouyang, W., & Wang, X. (2017). Zoom Out-and-In Network with Recursive Training for Object Proposal. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1702.05711

How many times has this paper been cited?

26 times, according to OpenAlex on 18 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 at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Hongyang Li, Yu Liu, Wanli Ouyang, Xiaogang Wang.

What is the DOI of this paper?

10.48550/arxiv.1702.05711, permanently at https://doi.org/10.48550/arxiv.1702.05711. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.