Triplet attention comprises of three branches each responsible for capturing crossdimension between the spatial dimensions and channel dimension of the input. Given an input tensor with shape (C × H × W), each branch is responsible for aggregating cross-dimensional interactive features between either the spatial dimension H or W and the channel dimension C.
Source: Rotate to Attend: Convolutional Triplet Attention ModulePaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Drug Discovery | 2 | 10.00% |
Object Detection | 2 | 10.00% |
Graph Learning | 1 | 5.00% |
Graph Property Prediction | 1 | 5.00% |
Graph Regression | 1 | 5.00% |
Link Prediction | 1 | 5.00% |
Molecular Property Prediction | 1 | 5.00% |
Property Prediction | 1 | 5.00% |
Computational Efficiency | 1 | 5.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |