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 | 36 | 12.90% |
Conditional Image Generation | 15 | 5.38% |
Object Detection | 11 | 3.94% |
Instance Segmentation | 10 | 3.58% |
Semantic Segmentation | 10 | 3.58% |
Super-Resolution | 7 | 2.51% |
Multi-agent Reinforcement Learning | 7 | 2.51% |
Reinforcement Learning (RL) | 6 | 2.15% |
Decision Making | 5 | 1.79% |
Component | Type |
|
---|---|---|
1x1 Convolution
|
Convolutions | |
Concatenation Affinity
|
Affinity Functions | (optional) |
Embedded Dot Product Affinity
|
Affinity Functions | (optional) |
Embedded Gaussian Affinity
|
Affinity Functions | (optional) |
Gaussian Affinity
|
Affinity Functions | (optional) |
Non-Local Operation
|
Image Feature Extractors | |
Residual Connection
|
Skip Connections |