An asymmetric non-local block that samples a small set of anchor points via pyramid pooling achieves similar or better segmentation accuracy than full non-local attention with large savings in compute and memory.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Asymmetric Non-local Neural Networks for Semantic Segmentation
An asymmetric non-local block that samples a small set of anchor points via pyramid pooling achieves similar or better segmentation accuracy than full non-local attention with large savings in compute and memory.