Research Area: Machine Learning
Small object detection is a challenging problem in computer vision. It has been widely applied in defense military, transportation, industry, etc. To facilitate in-depth understanding of small object detection, we comprehensively review the existing small object detection methods based on deep learning from five aspects, including multi-scale feature learning, data augmentation, training strategy, context-based detection and GAN-based detection. Then, we thoroughly analyze the performance of some typical small object detection algorithms on popular datasets, such as MS-COCO, PASCAL-VOC. Finally, the possible research directions in the future are pointed out from five perspectives: emerging small object detection datasets and benchmarks, multi-task joint learning and optimization, information transmission, weakly supervised small object detection methods and framework for small object detection task.
Keywords:
Author(s) Name: Kang Tong, Yiquan Wu, Fei Zhou
Journal name: Image and Vision Computing
Conferrence name:
Publisher name: Elsevier
DOI: 10.1016/j.imavis.2020.103910
Volume Information: Volume 97, May 2020, 103910
