The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919
Other
3.13k
stars
686
forks
source link
Is HRNet possible to segment multi-instance object? #201
HRNet is really a good network. Currently, I want to apply this network in my project. However, in one image, there may be several objects, and these objects may overlay. Is HRNet possible to segment multi-instance object?
HRNet is really a good network. Currently, I want to apply this network in my project. However, in one image, there may be several objects, and these objects may overlay. Is HRNet possible to segment multi-instance object?