Open daniel-j-h opened 5 years ago
We should look into the feature pyramid attention (FPA) module for pixel-precise attention for segmentation features extracted from our resnet encoder.
Pyramid Attention Network for Semantic Segmentation https://arxiv.org/abs/1805.10180
from https://arxiv.org/abs/1805.10180 Figure 2
from https://arxiv.org/abs/1805.10180 Figure 3
The GAU modules could be interesting to try out instead of our simple decoder modules, too.
We should look into the feature pyramid attention (FPA) module for pixel-precise attention for segmentation features extracted from our resnet encoder.
from https://arxiv.org/abs/1805.10180 Figure 2
from https://arxiv.org/abs/1805.10180 Figure 3
The GAU modules could be interesting to try out instead of our simple decoder modules, too.