Abstract

Scale variation is one of the key challenges in object detection. In this work, we first present a controlled experiment to investigate the effect of receptive fields for scale variation in object detection. Based on the findings from the exploration experiments, we propose a novel Trident Network (TridentNet) aiming to generate scale-specific feature maps with a uniform representational power. We construct a parallel multi-branch architecture in which each branch shares the same transformation parameters but with different receptive fields. Then, we adopt a scale-aware training scheme to specialize each branch by sampling object instances of proper scales for training. As a bonus, a fast approximation version of TridentNet could achieve significant improvements without any additional parameters and computational cost compared with the vanilla detector. On the COCO dataset, our TridentNet with ResNet-101 backbone achieves state-of-the-art single-model results of 48.4 mAP. Codes are available at https://git.io/fj5vR.

Keywords

Computer scienceObject detectionScale (ratio)Artificial intelligenceConstruct (python library)Object (grammar)Transformation (genetics)TridentFeature (linguistics)Sampling (signal processing)DetectorComputer visionScheme (mathematics)Pattern recognition (psychology)MathematicsGeography

Affiliated Institutions

Related Publications

Publication Info

Year
2019
Type
article
Pages
6053-6062
Citations
1012
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1012
OpenAlex

Cite This

Yanghao Li, Yuntao Chen, Naiyan Wang et al. (2019). Scale-Aware Trident Networks for Object Detection. , 6053-6062. https://doi.org/10.1109/iccv.2019.00615

Identifiers

DOI
10.1109/iccv.2019.00615