Single-fusion detector: Towards faster multi-scale object detection
College of Computer Studies
Proceedings - International Conference on Image Processing, ICIP
Despite recent improvements, the arbitrary sizes of objects still impede the predictive ability of object detectors. Recent solutions combine feature maps of different receptive fields to detect multi-scale objects. However, these methods have large computational costs resulting to slower inference time, which is not practical for real-time applications. Contrarily, fusion methods depending on large networks with many skip connections demand larger memory requirement, prohibiting usage in devices with limited memory. In this paper, we propose a more computationally efficient fusion method which integrates higher-order information to low-level feature maps using a single operation. Our method can flexibly adapt to any base network, allowing tailored performance for different computational requirements. Our approach achieves 81.7% mAP at 41 FPS on the PASCAL VOC dataset using ResNet-50 as the base network, which is superior in terms of both speed and mAP as compared to several state-of-the-art baselines, even those which use larger base networks. © 2019 IEEE.
Digitial Object Identifier (DOI)
Antioquia, A. C., Tan, D. S., Azcarraga, A., & Hua, K. (2019). Single-fusion detector: Towards faster multi-scale object detection. Proceedings - International Conference on Image Processing, ICIP, 2019-September, 76-80. https://doi.org/10.1109/ICIP.2019.8802913
Image converters; Neural networks (Computer science)