# DetNAS: Backbone Search for Object Detection

arXiv: https://arxiv.org/abs/1903.10979 · HTML: https://mlsanity.com/paper/1903.10979/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2019.

## Built on by (most cited first, 30 of 81)

- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond](https://mlsanity.com/paper/2101.11517/) (2021)
- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search](https://mlsanity.com/paper/2104.14545/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Neural Architecture Search for Spiking Neural Networks](https://mlsanity.com/paper/2201.10355/) (2022)
- [iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients](https://mlsanity.com/paper/2106.10784/) (2021)
- [Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism](https://mlsanity.com/paper/2309.11331/) (2023)
- [AutoSNN: Towards Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2201.12738/) (2022)
- [FEAR: Fast, Efficient, Accurate and Robust Visual Tracker](https://mlsanity.com/paper/2112.07957/) (2021)
- [DAMO-YOLO : A Report on Real-Time Object Detection Design](https://mlsanity.com/paper/2211.15444/) (2022)
- [Neural Architecture Search with Random Labels](https://mlsanity.com/paper/2101.11834/) (2021)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [Separable Self and Mixed Attention Transformers for Efficient Object Tracking](https://mlsanity.com/paper/2309.03979/) (2023)
- [Continual Forgetting for Pre-trained Vision Models](https://mlsanity.com/paper/2403.11530/) (2024)
- [AdvRush: Searching for Adversarially Robust Neural Architectures](https://mlsanity.com/paper/2108.01289/) (2021)
- [Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search](https://mlsanity.com/paper/2101.11342/) (2021)
- [GAIA: A Transfer Learning System of Object Detection that Fits Your Needs](https://mlsanity.com/paper/2106.11346/) (2021)
- [Multi-Scale Aligned Distillation for Low-Resolution Detection](https://mlsanity.com/paper/2109.06875/) (2021)
- [Scale-aware Automatic Augmentation for Object Detection](https://mlsanity.com/paper/2103.17220/) (2021)
- [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)
- [OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection](https://mlsanity.com/paper/2103.04507/) (2021)
- [G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection](https://mlsanity.com/paper/2402.04672/) (2024)
- [MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection](https://mlsanity.com/paper/2111.13336/) (2021)
- [PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution](https://mlsanity.com/paper/2204.11797/) (2022)
- [FBNetV5: Neural Architecture Search for Multiple Tasks in One Run](https://mlsanity.com/paper/2111.10007/) (2021)
- [DynamicDet: A Unified Dynamic Architecture for Object Detection](https://mlsanity.com/paper/2304.05552/) (2023)
- [Generalization Properties of NAS under Activation and Skip Connection Search](https://mlsanity.com/paper/2209.07238/) (2022)
- [Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation](https://mlsanity.com/paper/2104.15082/) (2021)

## Abstract (arXiv)

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNet pre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection. We train the supernet under the typical detector training schedule: ImageNet pre-training and detection fine-tuning. Then, the architecture search is performed on the trained supernet, using the detection task as the guidance. This framework makes NAS on backbones very efficient. In experiments, we show the effectiveness of DetNAS on various detectors, for instance, one-stage RetinaNet and the two-stage FPN. We empirically find that networks searched on object detection shows consistent superiority compared to those searched on ImageNet classification. The resulting architecture achieves superior performance than hand-crafted networks on COCO with much less FLOPs complexity.