ESNet is a lightweight symmetric CNN using factorized residual units and parallel dilated convolutions that reaches over 62 FPS semantic segmentation on Cityscapes with 1.6M parameters.
IJCV 111 (2015) 98–136
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
ESNet is a lightweight symmetric CNN using factorized residual units and parallel dilated convolutions that reaches over 62 FPS semantic segmentation on Cityscapes with 1.6M parameters.