Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild
Name:
IJCV_final_source_files.pdf
Size:
13.93Mb
Format:
PDF
Description:
Accepted manuscript
Type
ArticleKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionElectrical Engineering Program
VCC Analytics Research Group
Date
2020-02-18Online Publication Date
2020-02-18Print Publication Date
2020-06Embargo End Date
2021-02-18Submitted Date
2018-12-23Permanent link to this record
http://hdl.handle.net/10754/661946
Metadata
Show full item recordAbstract
Object detection results have been rapidly improved over a short period of time with the development of deep convolutional neural networks. Although impressive results have been achieved on large/medium sized objects, the performance on small objects is far from satisfactory and one of remaining open challenges is detecting small object in unconstrained conditions (e.g. COCO and WIDER FACE benchmarks). The reason is that small objects usually lack sufficient detailed appearance information, which can distinguish them from the backgrounds or similar objects. To deal with the small object detection problem, in this paper, we propose an end-to-end multi-task generative adversarial network (MTGAN), which is a general framework. In the MTGAN, the generator is a super-resolution network, which can up-sample small blurred images into fine-scale ones and recover detailed information for more accurate detection. The discriminator is a multi-task network, which describes each inputted image patch with a real/fake score, object category scores, and bounding box regression offsets. Furthermore, to make the generator recover more details for easier detection, the classification and regression losses in the discriminator are back-propagated into the generator during training process. Extensive experiments on the challenging COCO and WIDER FACE datasets demonstrate the effectiveness of the proposed method in restoring a clear super-resolved image from a blurred small one, and show that the detection performance, especially for small sized objects, improves over state-of-the-art methods by a large margin.Citation
Zhang, Y., Bai, Y., Ding, M., & Ghanem, B. (2020). Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild. International Journal of Computer Vision. doi:10.1007/s11263-020-01301-6Sponsors
The majority of this work was done when Yongqiang Zhang was a visiting Ph.D. student at King Abdullah University of Science and Technology (KAUST), and the others are continued at Harbin Institute of Technology (HIT). This work was supported by Natural Science Foundation of China, Grant No. 61603372.Publisher
Springer NatureAdditional Links
http://link.springer.com/10.1007/s11263-020-01301-6ae974a485f413a2113503eed53cd6c53
10.1007/s11263-020-01301-6