Fast Voxel Query is a module used in the Voxel Transformer 3D object detection model implementation of self-attention, specifically Local and Dilated Attention. For each querying index $v_{i}$, an attending voxel index $v_{j}$ is determined by Local and Dilated Attention. Then we can lookup the non-empty index $j$ in the hash table with hashed $v_{j}$ as the key. Finally, the non-empty index $j$ is used to gather the attending feature $f_{j}$ from $\mathcal{F}$ for multi-head attention.
Source: Voxel Transformer for 3D Object DetectionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
3D Object Detection | 1 | 25.00% |
Computational Efficiency | 1 | 25.00% |
Object Detection | 1 | 25.00% |
Object Recognition | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |