Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
By Yu Wang, Quan Zhou, Jia Liu, Jian Xiong, Guangwei Gao, Xiaofu Wu, Longin Jan Latecki. International Conference on Information Photonics, 2019
385 citations recorded by the source corpus.
The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation. More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters, and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/1d327de48c02f886303c1b7627724d4ed795ad91
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Sheng Tang
- Tianyi Wu
- Horst-Michael Groß
- Benjamin Lewandowski
- Yongdong Zhang
- Mona Köhler
- Tim Wengefeld
- Daniel Seichter
Citations in the corpus
- Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis (2020, methodology): “Efficient approaches with custom architectures such as ERFNet [26], LEDNet [27], and ESPNetv2 [32] are quite”
- CGNet: A Light-Weight Context Guided Network for Semantic Segmentation (2018, methodology): “LEDNet [27] introduced an asymmetric encoder-decoder architecture, and utilized channel split and shuffle for reducing”