Speed/accuracy trade-offs for modern convolutional object detectors

Code

• github.com/IBM/MAX-Object-Detector
  tf★ 0
• github.com/jiportilla/edge-max-object-detector
  tf★ 0
• github.com/yuhsijen/Object-Detector
  tf★ 0
• github.com/sdkchris/Exercise-Sheet-1
  tf★ 0
• github.com/Qengineering/TensorFlow_Lite_RPi_64-bits
  tf★ 0
• github.com/Qengineering/MobileNetV1_SSD_OpenCV_Caffe
  none★ 0
• github.com/Qengineering/TensorFlow_Lite_SSD_RPi_64-bits
  tf★ 0
• github.com/Qengineering/TensorFlow_Lite_SSD_RPi_32-bits
  tf★ 0
• github.com/Qengineering/MobileNet_SSD_OpenCV_TensorFlow
  tf★ 0
• github.com/rajatashhpa/1
  tf★ 0

Abstract

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-to-apples 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 [Ren et al., 2015], R-FCN [Dai et al., 2016] and SSD [Liu et al., 2015] 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.

Tasks

Reproductions