EC-CNN uses a gated feature-wise transform to incorporate edge priors for thermal semantic segmentation and introduces the SODA dataset of over 7,000 labeled thermal images.
Large kernel matters iimprove semantic segmentation by global convolutional network,
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
-
Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation
EC-CNN uses a gated feature-wise transform to incorporate edge priors for thermal semantic segmentation and introduces the SODA dataset of over 7,000 labeled thermal images.