ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network

11/28/2018
by   Sachin Mehta, et al.
10

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. Our code is open-source and available at <https://github.com/sacmehta/ESPNetv2>

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/08/2019

DiCENet: Dimension-wise Convolutions for Efficient Networks

In this paper, we propose a new CNN model DiCENet, that is built using: ...
research
05/26/2023

SSSegmenation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch

This paper presents SSSegmenation, which is an open source supervised se...
research
10/04/2022

FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions

In this work we present FreDSNet, a deep learning solution which obtains...
research
05/19/2023

JetSeg: Efficient Real-Time Semantic Segmentation Model for Low-Power GPU-Embedded Systems

Real-time semantic segmentation is a challenging task that requires high...
research
05/17/2023

Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network

Filter-decomposition-based group-equivariant convolutional neural networ...
research
06/02/2021

A Generalizable Approach to Learning Optimizers

A core issue with learning to optimize neural networks has been the lack...
research
03/22/2022

Focal Modulation Networks

In this work, we propose focal modulation network (FocalNet in short), w...

Please sign up or login with your details

Forgot password? Click here to reset