Learning Implicit Feature Alignment Function for Semantic Segmentation. (arXiv:2206.08655v1 [cs.CV])

Web: http://arxiv.org/abs/2206.08655

Integrating high-level context information with low-level details is of
central importance in semantic segmentation. Towards this end, most existing
segmentation models apply bilinear up-sampling and convolutions to feature maps
of different scales, and then align them at the same resolution. However,
bilinear up-sampling blurs the precise information learned in these feature
maps and convolutions incur extra computation costs. To address these issues,
we propose the Implicit Feature Alignment function (IFA). Our method is
inspired by the rapidly expanding topic of …

arxiv cv feature function learning segmentation semantic