Aggregation of Masked Outputs for Improving Accuracy–Cost Trade-Off in Semantic Segmentation
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3265077
Abstract: Downsampling layers are essential for convolutional neural network-based semantic segmentation methods to widen their receptive fields. However, as fine-grained information is lost in the layers, the accuracy of these methods becomes limited. The need for… read more here.
Keywords: semantic segmentation; computational cost; intermediate outputs; cost ... See more keywords