Next Article in Journal
Ultrafast and Energy-saving Synthesis of Nitrogen and Chlorine Co-doped Carbon Nanodots via Neutralization Heat for Selective Detection of Cr(VI) in Aqueous Phase
Next Article in Special Issue
High-Resolution Aerial Imagery Semantic Labeling with Dense Pyramid Network
Previous Article in Journal
Value of Information Based Data Retrieval in UWSNs
Previous Article in Special Issue
Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images
Article Menu
Issue 10 (October) cover image

Export Article

Open AccessArticle
Sensors 2018, 18(10), 3415;

Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection

Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, and Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing 100190, China
University of Chinese Academy of Sciences, Beijing 100049, China
State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, China
Author to whom correspondence should be addressed.
Received: 27 August 2018 / Revised: 2 October 2018 / Accepted: 5 October 2018 / Published: 11 October 2018
(This article belongs to the Special Issue Sensors Signal Processing and Visual Computing)
Full-Text   |   PDF [2702 KB, uploaded 17 October 2018]   |  


In the image object detection task, a huge number of candidate boxes are generated to match with a relatively very small amount of ground-truth boxes, and through this method the learning samples can be created. But in fact the vast majority of the candidate boxes do not contain valid object instances and should be recognized and rejected during the training and evaluation of the network. This leads to extra high computation burden and a serious imbalance problem between object and none-object samples, thereby impeding the algorithm’s performance. Here we propose a new heuristic sampling method to generate candidate boxes for two-stage detection algorithms. It is generally applicable to the current two-stage detection algorithms to improve their detection performance. Experiments on COCO dataset showed that, relative to the baseline model, this new method could significantly increase the detection accuracy and efficiency. View Full-Text
Keywords: image object detection; RCNN; Faster RCNN; Light Head RCNN image object detection; RCNN; Faster RCNN; Light Head RCNN

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Zhang, J.; Zhang, J.; Yu, S. Hot Anchors: A Heuristic Anchors Sampling Method in RCNN-Based Object Detection. Sensors 2018, 18, 3415.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Sensors EISSN 1424-8220 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top