Feature Extractors
Neural Attention Fields
Introduced by Chitta et al. in NEAT: Neural Attention Fields for End-to-End Autonomous DrivingNEAT, or Neural Attention Fields, is a feature representation for end-to-end imitation learning models. NEAT is a continuous function which maps locations in Bird's Eye View (BEV) scene coordinates to waypoints and semantics, using intermediate attention maps to iteratively compress high-dimensional 2D image features into a compact representation. This allows the model to selectively attend to relevant regions in the input while ignoring information irrelevant to the driving task, effectively associating the images with the BEV representation. Furthermore, visualizing the attention maps for models with NEAT intermediate representations provides improved interpretability.
Source: NEAT: Neural Attention Fields for End-to-End Autonomous Driving
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Novel View Synthesis | 2 | 14.29% |
| Reinforcement Learning (RL) | 2 | 14.29% |
| Computational Efficiency | 1 | 7.14% |
| Active Learning | 1 | 7.14% |
| Classification | 1 | 7.14% |
| 3D Reconstruction | 1 | 7.14% |
| 3D Wireframe Reconstruction | 1 | 7.14% |
| Atari Games | 1 | 7.14% |
| Evolutionary Algorithms | 1 | 7.14% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
