Scale Match for Tiny Person Detection

Xuehui Yu, Yuqi Gong, Nan Jiang, Qixiang Ye, Zhenjun Han; The IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 1257-1265

Abstract


Visual object detection has achieved unprecedented advance with the rise of deep convolutional neural networks.However, detecting tiny objects (for example tiny persons less than 20 pixels) in large-scale images remains challenging. The extremely small objects raise a grand challenge about feature representation while the massive and complex backgrounds aggregates the risk of false detections. In this paper, we introduce a new benchmark, referred to as TinyPerson, opening up a promising direction for tiny object detection in a long distance and with massive back-grounds. We experimentally find that the scale mismatch be-tween the dataset for network pretraining and the dataset for detector learning could deteriorate the feature representation and the detectors. Accordingly, we propose a simple yet effective Scale Match approach to align the object scales between the two datasets for favorable tiny-object representation. Experiments show the significant performance gain of our proposed approach over state-of-the-art detectors, and the challenging aspects of TinyPerson related to real-world scenarios. The TinyPerson benchmark and the code for our approach will be publicly available.

Related Material


[pdf]
[bibtex]
@InProceedings{Yu_2020_WACV,
author = {Yu, Xuehui and Gong, Yuqi and Jiang, Nan and Ye, Qixiang and Han, Zhenjun},
title = {Scale Match for Tiny Person Detection},
booktitle = {The IEEE Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}