# Representation Sharing for Fast Object Detector Search and Beyond

arXiv: https://arxiv.org/abs/2007.12075 · HTML: https://mlsanity.com/paper/2007.12075/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [Exploring Classification Equilibrium in Long-Tailed Object Detection](https://mlsanity.com/paper/2108.07507/) (2021)
- [G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection](https://mlsanity.com/paper/2402.04672/) (2024)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [NAS-FCOS: Efficient Search for Object Detection Architectures](https://mlsanity.com/paper/2110.12423/) (2021)
- [Unchain the Search Space with Hierarchical Differentiable Architecture Search](https://mlsanity.com/paper/2101.04028/) (2021)
- [Efficient Visual Fault Detection for Freight Train via Neural Architecture Search with Data Volume Robustness](https://mlsanity.com/paper/2405.17004/) (2024)
- [Mutually-aware Sub-Graphs Differentiable Architecture Search](https://mlsanity.com/paper/2107.04324/) (2021)

## Abstract (arXiv)

Region Proposal Network (RPN) provides strong support for handling the scale variation of objects in two-stage object detection. For one-stage detectors which do not have RPN, it is more demanding to have powerful sub-networks capable of directly capturing objects of unknown sizes. To enhance such capability, we propose an extremely efficient neural architecture search method, named Fast And Diverse (FAD), to better explore the optimal configuration of receptive fields and convolution types in the sub-networks for one-stage detectors. FAD consists of a designed search space and an efficient architecture search algorithm. The search space contains a rich set of diverse transformations designed specifically for object detection. To cope with the designed search space, a novel search algorithm termed Representation Sharing (RepShare) is proposed to effectively identify the best combinations of the defined transformations. In our experiments, FAD obtains prominent improvements on two types of one-stage detectors with various backbones. In particular, our FAD detector achieves 46.4 AP on MS-COCO (under single-scale testing), outperforming the state-of-the-art detectors, including the most recent NAS-based detectors, Auto-FPN (searched for 16 GPU-days) and NAS-FCOS (28 GPU-days), while significantly reduces the search cost to 0.6 GPU-days. Beyond object detection, we further demonstrate the generality of FAD on the more challenging instance segmentation, and expect it to benefit more tasks.