# Computation Reallocation for Object Detection

arXiv: https://arxiv.org/abs/1912.11234 · HTML: https://mlsanity.com/paper/1912.11234/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2019.

## Built on by (most cited first, 17 of 17)

- [Sample and Computation Redistribution for Efficient Face Detection](https://mlsanity.com/paper/2105.04714/) (2021)
- [TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search](https://mlsanity.com/paper/2105.11871/) (2021)
- [GLiT: Neural Architecture Search for Global and Local Image Transformer](https://mlsanity.com/paper/2107.02960/) (2021)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search](https://mlsanity.com/paper/2105.10154/) (2021)
- [ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild](https://mlsanity.com/paper/2208.11547/) (2022)
- [PSViT: Better Vision Transformer via Token Pooling and Attention Sharing](https://mlsanity.com/paper/2108.03428/) (2021)
- [BN-NAS: Neural Architecture Search with Batch Normalization](https://mlsanity.com/paper/2108.07375/) (2021)
- [Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2208.05271/) (2022)
- [NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models](https://mlsanity.com/paper/2108.03434/) (2021)
- [NAS-FCOS: Efficient Search for Object Detection Architectures](https://mlsanity.com/paper/2110.12423/) (2021)
- [DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions](https://mlsanity.com/paper/2403.01326/) (2024)
- [Unchain the Search Space with Hierarchical Differentiable Architecture Search](https://mlsanity.com/paper/2101.04028/) (2021)
- [Dilated SpineNet for Semantic Segmentation](https://mlsanity.com/paper/2103.12270/) (2021)
- [Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight](https://mlsanity.com/paper/2105.08994/) (2021)
- [One Network Doesn't Rule Them All: Moving Beyond Handcrafted Architectures in Self-Supervised Learning](https://mlsanity.com/paper/2203.08130/) (2022)
- [Learning Cross-modality Information Bottleneck Representation for Heterogeneous Person Re-Identification](https://mlsanity.com/paper/2308.15063/) (2023)

## Abstract (arXiv)

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.