Introduces FSS and DD Block techniques that boost accuracy for distinguishing lane types in semantic segmentation while matching or exceeding baseline speed on high-resolution images.
Multi -scale context aggregation by dilated convolutions,
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
-
Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks
Introduces FSS and DD Block techniques that boost accuracy for distinguishing lane types in semantic segmentation while matching or exceeding baseline speed on high-resolution images.