ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network
Abstract
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 four different tasks: (1) object classification, (2) semantic segmentation, (3) object detection, and (4) 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 outperforms ES-PNet by 4-5% and has 2-4x fewer FLOPs on the PASCAL VOC and the Cityscapes dataset. Compared to YOLOv2 on the MS-COCO object detection, ESPNetv2 delivers 4.4% higher accuracy with 6x fewer FLOPs. Our experiments show that ESPNetv2 is much more power efficient than existing state-of-the-art efficient methods including ShuffleNets and MobileNets.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 16, 2019
- Accession Number
- AD1152099
Entities
People
- Hannaneh Hajishirzi
- Linda Shapiro
- Mohammad Rastegari
- Sachin Mehta
Organizations
- Allen Institute for Artificial Intelligence
- University of Washington