Efficient ConvNet for real-time semantic segmentation
By Eduardo Romera, José Manuel Álvarez, Luis Miguel Bergasa, Roberto Arroyo. 2017
101 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Bernard Ghanem
- Vladlen Koltun
- Amos J. Storkey
- Sergey Levine
- Elliot J. Crowley
- Matthias Müller
- Gavia Gray
- José Manuel Álvarez
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Chunhua Shen
- Dacheng Tao
- Ming-Hsuan Yang
- Trevor Darrell
- Yi Yang
- Jingdong Wang
- Bernard Ghanem
Citations in the corpus
- Driving Policy Transfer via Modularity and Abstraction (2018, methodology): “This demonstrates that our architecture is well-suited to the task at hand, roughly matching ERFNet in accuracy while running at 40% higher frame rate.”
- Moonshine: Distilling with Cheap Convolutions (2017, methodology): “For our teacher network we use an ERFNet (Romera et al., 2017a,b) a 3 × 1 convolution followed by a 1 × 3 convolution.”
- Structured Knowledge Distillation for Semantic Segmentation (2019, methodology): “Blue circles are collected from FCN* [38], RefineNet [23], SegNet [3], ENet [31], PSPNet [56], ERFNet [34], ESPNet [28], MobileNetV2Plus [25], and OCNet [50].”
- ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation (2018, methodology): “This paper is an extension of our conference paper [14], which has been extended with a detailed description of the proposed residual block and the full architecture ERFNet, along with an extended set of experiments.”
- CNN-based Fisheye Image Real-Time Semantic Segmentation (2018, background): “Our ERFNet [17] proposal presents a ”wider” (as op-”