Rethinking the Backbone Architecture for Tiny Object Detection

Jinlai Ning, Haoyan Guan, Michael Spratling

2023

Abstract

Tiny object detection has become an active area of research because images with tiny targets are common in several important real-world scenarios. However, existing tiny object detection methods use standard deep neural networks as their backbone architecture. We argue that such backbones are inappropriate for detecting tiny objects as they are designed for the classification of larger objects, and do not have the spatial resolution to identify small targets. Specifically, such backbones use max-pooling or a large stride at early stages in the architecture. This produces lower resolution feature-maps that can be efficiently processed by subsequent layers. However, such low-resolution feature-maps do not contain information that can reliably discriminate tiny objects. To solve this problem we design “bottom-heavy” versions of backbones that allocate more resources to processing higher-resolution features without introducing any additional computational burden overall. We also investigate if pre-training these backbones on images of appropriate size, using CIFAR100 and ImageNet32, can further improve performance on tiny object detection. Results on TinyPerson and WiderFace show that detectors with our proposed backbones achieve better results than the current state-of-the-art methods.

Paper Citation

in Harvard Style

Ning J., Guan H. and Spratling M. (2023). Rethinking the Backbone Architecture for Tiny Object Detection. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 103-114. DOI: 10.5220/0011643500003417

in Bibtex Style

@conference{visapp23,
author={Jinlai Ning and Haoyan Guan and Michael Spratling},
title={Rethinking the Backbone Architecture for Tiny Object Detection},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={103-114},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011643500003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Rethinking the Backbone Architecture for Tiny Object Detection
SN - 978-989-758-634-7
AU - Ning J.
AU - Guan H.
AU - Spratling M.
PY - 2023
SP - 103
EP - 114
DO - 10.5220/0011643500003417
PB - SciTePress