Method Details

Details for method 'ESPNetv2'

name	ESPNetv2
challenge	pixel-level semantic labeling
details	We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise dilated separable convolutions to learn representations from a large effective receptive field with fewer FLOPs and parameters. The performance of our network is evaluated on three different tasks: (1) object classification, (2) semantic segmentation, and (3) language modeling. Experiments on these tasks, including image classification on the ImageNet and language modeling on the PenTree bank dataset, demonstrate the superior performance of our method over the state-of-the-art methods. Our network has better generalization properties than ShuffleNetv2 when tested on the MSCOCO multi-object classification task and the Cityscapes urban scene semantic segmentation task. Our experiments show that ESPNetv2 is much more power efficient than existing state-of-the-art efficient methods including ShuffleNets and MobileNets.
publication	ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network Sachin Mehta, Mohammad Rastegari, Linda Shapiro, Hannaneh Hajishirzi https://arxiv.org/abs/1811.11431
project page / code	https://github.com/sacmehta/ESPNetv2
used Cityscapes data	fine annotations
used external data	ImageNet
runtime	0.012 s NVIDIA TitanX GPU
subsampling	2
submission date	November, 2018
previous submissions