A Non-Local Block is an image block module used in neural networks that wraps a non-local operation. We can define a non-local block as:
$$ \mathbb{z}_{i} = W_{z}\mathbb{y_{i}} + \mathbb{x}_{i} $$
where $y_{i}$ is the output from the non-local operation and $+ \mathbb{x}_{i}$ is a residual connection.
Source: Non-local Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 31 | 17.92% |
Conditional Image Generation | 13 | 7.51% |
Instance Segmentation | 10 | 5.78% |
Semantic Segmentation | 10 | 5.78% |
Object Detection | 10 | 5.78% |
Super-Resolution | 6 | 3.47% |
Image Super-Resolution | 4 | 2.31% |
Image Classification | 4 | 2.31% |
Action Recognition | 4 | 2.31% |
Component | Type |
|
---|---|---|
![]() |
Convolutions | |
![]() |
Affinity Functions | (optional) |
![]() |
Affinity Functions | (optional) |
![]() |
Affinity Functions | (optional) |
![]() |
Affinity Functions | (optional) |
![]() |
Image Feature Extractors | |
![]() |
Skip Connections |