Simple and Efficient Architectures for Semantic Segmentation. (arXiv:2206.08236v1 [cs.CV])

Web: http://arxiv.org/abs/2206.08236

Though the state-of-the architectures for semantic segmentation, such as
HRNet, demonstrate impressive accuracy, the complexity arising from their
salient design choices hinders a range of model acceleration tools, and further
they make use of operations that are inefficient on current hardware. This
paper demonstrates that a simple encoder-decoder architecture with a
ResNet-like backbone and a small multi-scale head, performs on-par or better
than complex semantic segmentation architectures such as HRNet, FANet and
DDRNets. Naively applying deep backbones designed for Image …

arxiv cv segmentation semantic