Semantic Scholar Open Access 2016 2667 sitasi

Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors

Jonathan Huang V. Rathod Chen Sun Menglong Zhu Anoop Korattikara Balan +6 lainnya

Abstrak

The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-toapples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN [30], R-FCN [6] and SSD [25] systems, which we view as meta-architectures and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.

Topik & Kata Kunci

Penulis (11)

J

Jonathan Huang

V

V. Rathod

C

Chen Sun

M

Menglong Zhu

A

Anoop Korattikara Balan

A

A. Fathi

I

Ian S. Fischer

Z

Z. Wojna

Y

Yang Song

S

S. Guadarrama

K

K. Murphy

Format Sitasi

Huang, J., Rathod, V., Sun, C., Zhu, M., Balan, A.K., Fathi, A. et al. (2016). Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors. https://doi.org/10.1109/CVPR.2017.351

Akses Cepat

Lihat di Sumber doi.org/10.1109/CVPR.2017.351
Informasi Jurnal
Tahun Terbit
2016
Bahasa
en
Total Sitasi
2667×
Sumber Database
Semantic Scholar
DOI
10.1109/CVPR.2017.351
Akses
Open Access ✓