Computation Reallocation for Object Detection

By Feng Liang, Chen Lin, Ronghao Guo, Ming Sun, Wei Wu, Junjie Yan, Wanli Ouyang. 2019

36 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiaojun Chang
2. Xiaodan Liang
3. Liang Lin
4. Junjie Yan
5. Wanli Ouyang
6. Po-Yao (Bernie) Huang
7. Zhihui Li
8. Xiaojiang Chen

In Computer Vision and Pattern Recognition

1. Xiaodan Liang
2. Liang Lin
3. Xiaogang Wang
4. Wanli Ouyang
5. Luc Van Gool
6. Yi Yang
7. Xiaojun Chang
8. Dacheng Tao

Citations in the corpus

• A Comprehensive Survey of Neural Architecture Search (2020, methodology): “With the improvement of NAS search efficiency, NAS is also quickly applied in the fields of object detection [65, 75, 111, 118], semantic segmentation [63, 64, 120], adversarial learning [53], architectural scaling [114, 122, 124], multi-objective optimization [39, 115, 125], platform-aware [28,…”
• Block-Wisely Supervised Neural Architecture Search With Knowledge Distillation (2019, methodology): “Instead, [20] searches for layer numbers with fixed operations first, and subsequently searches for operations with a fixed layer number.”
• Dilated SpineNet for Semantic Segmentation (2021, methodology): “Recent architectures discovered by NAS have shown promising results than handcrafted models on vision tasks including image classification [57, 31, 41, 20], object detection [16, 14, 13, 23, 43, 46, 24], semantic segmentation [27, 34], etc.”
• GLiT: Neural Architecture Search for Global and Local Image Transformer (2021, methodology): “Recently, NAS methods make great progress on the vision tasks [5, 9, 23, 35, 20, 21].”