Computation Reallocation for Object Detection
Abstract
The allocation of computation resources in the backbone is a crucial issue in object detection. However, classification allocation pattern is usually adopted directly to object detector, which is proved to be sub-optimal. In order to reallocate the engaged computation resources in a more efficient way, we present CR-NAS (Computation Reallocation Neural Architecture Search) that can learn computation reallocation strategies across different feature resolution and spatial position diectly on the target detection dataset. A two-level reallocation space is proposed for both stage and spatial reallocation. A novel hierarchical search procedure is adopted to cope with the complex search space. We apply CR-NAS to multiple backbones and achieve consistent improvements. Our CR-ResNet50 and CR-MobileNetV2 outperforms the baseline by 1.9% and 1.7% COCO AP respectively without any additional computation budget. The models discovered by CR-NAS can be equiped to other powerful detection neck/head and be easily transferred to other dataset, e.g. PASCAL VOC, and other vision tasks, e.g. instance segmentation. Our CR-NAS can be used as a plugin to improve the performance of various networks, which is demanding.
Cite
Text
Liang et al. "Computation Reallocation for Object Detection." International Conference on Learning Representations, 2020.Markdown
[Liang et al. "Computation Reallocation for Object Detection." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/liang2020iclr-computation/)BibTeX
@inproceedings{liang2020iclr-computation,
title = {{Computation Reallocation for Object Detection}},
author = {Liang, Feng and Lin, Chen and Guo, Ronghao and Sun, Ming and Wu, Wei and Yan, Junjie and Ouyang, Wanli},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/liang2020iclr-computation/}
}