Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving

11 Aug 2020 Xiaofeng Liu Yimeng Zhang Xiongchang Liu Song Bai Site Li Jane You

Semantic segmentation is important for many real-world systems, e.g., autonomous vehicles, which predict the class of each pixel. Recently, deep networks achieved significant progress w.r.t... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
CARLA
Video Game Models
Dense Connections
Feedforward Networks
SpatialDropout
Regularization
PReLU
Activation Functions
Feedforward Network
Feedforward Networks
ENet Bottleneck
Image Model Blocks
1x1 Convolution
Convolutions
CRF
Structured Prediction
ENet Dilated Bottleneck
Image Model Blocks
Dilated Convolution
Convolutions
Max Pooling
Pooling Operations
Softmax
Output Functions
Convolution
Convolutions
ENet Initial Block
Image Model Blocks
ENet
Semantic Segmentation Models
Batch Normalization
Normalization
DeepLab
Semantic Segmentation Models
ReLU
Activation Functions
Kaiming Initialization
Initialization
SegNet
Semantic Segmentation Models
FCN
Semantic Segmentation Models