Reading: SqueezeNext — Hardware-Aware Neural Network Design (Image Classification)

Original article was published by Sik-Ho Tsang on Artificial Intelligence on Medium


Reading: SqueezeNext — Hardware-Aware Neural Network Design (Image Classification)

In this story, SqueezeNext: Hardware-Aware Neural Network Design, by UC Berkeley, is briefly presented. This network, SqueezeNext:

  • matches AlexNet’s accuracy on the ImageNet benchmark with 112× fewer parameters.
  • achieves VGG-19 accuracy with only 4.4 Million parameters, 31× smaller than VGG-19.
  • achieves better top-5 classification accuracy with 1.3 fewer parameters as compared to MobileNetV1, but avoids using depthwise-separable convolutions that are inefficient on some mobile processor platforms.
  • is 2.59/8.26 faster and 2.25/7.5 more energy efficient as compared to SqueezeNet/AlexNet without any accuracy degradation.

This is a paper in 2018 CVPRW with over 80 citations. (Sik-Ho Tsang @ Medium)