DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter
This addresses the computational burden of neural architecture search for object detection, though it is an incremental improvement on existing once-for-all methods.
The paper tackles the challenge of efficiently training supernets for object detection with limited data by proposing a search space pruning method using a resource-constrained performance predictor called path filter, which reduces computational cost by 30-63% and improves average precision by 0.85-0.45 points on Pascal VOC and COCO datasets.
We address the challenge of training a large supernet for the object detection task, using a relatively small amount of training data. Specifically, we propose an efficient supernet-based neural architecture search (NAS) method that uses search space pruning. The search space defined by the supernet is pruned by removing candidate models that are predicted to perform poorly. To effectively remove the candidates over a wide range of resource constraints, we particularly design a performance predictor for supernet, called path filter, which is conditioned by resource constraints and can accurately predict the relative performance of the models that satisfy similar resource constraints. Hence, supernet training is more focused on the best-performing candidates. Our path filter handles prediction for paths with different resource budgets. Compared to once-for-all, our proposed method reduces the computational cost of the optimal network architecture by 30% and 63%, while yielding better accuracy-floating point operations Pareto front (0.85 and 0.45 points of improvement on average precision for Pascal VOC and COCO, respectively).