Neural Architecture Search
DetNAS
Introduced by Chen et al. in DetNAS: Backbone Search for Object DetectionDetNAS is a neural architecture search algorithm for the design of better backbones for object detection. It is based on the technique of one-shot supernet, which contains all possible networks in the search space. The supernet is trained under the typical detector training schedule: ImageNet pre-training and detection fine-tuning. Then, the architecture search is performed on the trained supernet, using the detection task as the guidance. DetNAS uses evolutionary search as opposed to RL-based methods or gradient-based methods.
Source: DetNAS: Backbone Search for Object Detection
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 3 | 37.50% |
| General Classification | 2 | 25.00% |
| Image Classification | 2 | 25.00% |
| Semantic Segmentation | 1 | 12.50% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
