DetNAS

2000년 도입 · 논문 3편에서 사용

DetNAS 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.

출처: DetNAS: Backbone Search for Object Detection

소개 논문: DetNAS: Backbone Search for Object Detection