ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network
@article{Mehta2019ESPNetv2AL, title={ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network}, author={Sachin Mehta and M. Rastegari and L. Shapiro and Hannaneh Hajishirzi}, journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2019}, pages={9182-9192} }
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. [...] Key Result 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.Expand Abstract
Supplemental Code
Github Repo
Via Papers with Code
A light-weight, power efficient, and general purpose convolutional neural network
Github Repo
Via Papers with Code
Sandbox for training convolutional networks for computer vision
Figures, Tables, and Topics from this paper
76 Citations
Segmenting 2K-Videos at 36.5 FPS with 24.3 GFLOPs: Accurate and Lightweight Realtime Semantic Segmentation Network
- Computer Science
- 2020 IEEE International Conference on Robotics and Automation (ICRA)
- 2020
- 1
- PDF
FDDWNet: A Lightweight Convolutional Neural Network for Real-Time Semantic Segmentation
- Computer Science
- ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
- 2020
- 2
- PDF
DSNet: An Efficient CNN for Road Scene Segmentation
- Computer Science
- 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
- 2019
- 6
- PDF
Efficient Semantic Segmentation Using Spatio-Channel Dilated Convolutions
- Computer Science
- IEEE Access
- 2019
- 2
- Highly Influenced
- PDF
A comprehensive survey on model compression and acceleration
- Computer Science
- Artificial Intelligence Review
- 2020
- 17
Butterfly Transform: An Efficient FFT Based Neural Architecture Design
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 4
- PDF
LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution
- Computer Science
- ArXiv
- 2019
- 2
- PDF
DenseLightNet: A Light-Weight Vehicle Detection Network for Autonomous Driving
- Computer Science
- IEEE Transactions on Industrial Electronics
- 2020
- 4
References
SHOWING 1-10 OF 69 REFERENCES
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
- Computer Science
- ECCV
- 2018
- 212
- PDF
Understanding Convolution for Semantic Segmentation
- Computer Science
- 2018 IEEE Winter Conference on Applications of Computer Vision (WACV)
- 2018
- 556
- PDF
IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
- Computer Science
- BMVC
- 2018
- 58
- PDF
Going deeper with convolutions
- Computer Science
- 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- 2015
- 21,907
- PDF
ImageNet classification with deep convolutional neural networks
- Computer Science
- Commun. ACM
- 2012
- 58,440
- PDF
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Computer Science
- 2015 IEEE International Conference on Computer Vision (ICCV)
- 2015
- 8,860
- PDF
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2018
- 6,039
- PDF
ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation
- Computer Science
- IEEE Transactions on Intelligent Transportation Systems
- 2018
- 359
- PDF
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2017
- 5,319
- PDF