# MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

arXiv: https://arxiv.org/abs/2004.14525 · HTML: https://mlsanity.com/paper/2004.14525/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 30 of 55)

- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Characterizing signal propagation to close the performance gap in unnormalized ResNets](https://mlsanity.com/paper/2101.08692/) (2021)
- [HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark](https://mlsanity.com/paper/2103.10584/) (2021)
- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Rethinking Text Line Recognition Models](https://mlsanity.com/paper/2104.07787/) (2021)
- [ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design](https://mlsanity.com/paper/2210.09573/) (2022)
- [NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge](https://mlsanity.com/paper/2103.11470/) (2021)
- [A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects](https://mlsanity.com/paper/2305.07348/) (2023)
- [Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference](https://mlsanity.com/paper/2211.10526/) (2022)
- [PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices](https://mlsanity.com/paper/2111.00902/) (2021)
- [MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection](https://mlsanity.com/paper/2111.13336/) (2021)
- [FBNetV5: Neural Architecture Search for Multiple Tasks in One Run](https://mlsanity.com/paper/2111.10007/) (2021)
- [Object Detection in Autonomous Vehicles: Status and Open Challenges](https://mlsanity.com/paper/2201.07706/) (2022)
- [Rethinking Co-design of Neural Architectures and Hardware Accelerators](https://mlsanity.com/paper/2102.08619/) (2021)
- [YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs](https://mlsanity.com/paper/2110.13713/) (2021)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [A Survey on Computationally Efficient Neural Architecture Search](https://mlsanity.com/paper/2206.01520/) (2022)
- [RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks](https://mlsanity.com/paper/2206.06637/) (2022)
- [Oriented object detection in optical remote sensing images using deep learning: a survey](https://mlsanity.com/paper/2302.10473/) (2023)
- [Filtering Empty Camera Trap Images in Embedded Systems](https://mlsanity.com/paper/2104.08859/) (2021)
- [NAS-FCOS: Efficient Search for Object Detection Architectures](https://mlsanity.com/paper/2110.12423/) (2021)
- [Restructurable Activation Networks](https://mlsanity.com/paper/2208.08562/) (2022)
- [Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptation](https://mlsanity.com/paper/2210.09739/) (2022)
- [A Comprehensive Evaluation of Deep Learning Object Detection Models on Heterogeneous Edge Devices](https://mlsanity.com/paper/2409.16808/) (2024)
- [3D Semantic Scene Perception using Distributed Smart Edge Sensors](https://mlsanity.com/paper/2205.01460/) (2022)
- [DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention](https://mlsanity.com/paper/2209.13933/) (2022)
- [Toward Edge-Efficient Dense Predictions with Synergistic Multi-Task Neural Architecture Search](https://mlsanity.com/paper/2210.01384/) (2022)
- [SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device](https://mlsanity.com/paper/2308.08137/) (2023)
- [Deep Learning for Real Time Satellite Pose Estimation on Low Power Edge TPU](https://mlsanity.com/paper/2204.03296/) (2022)

## Abstract (arXiv)

Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimality of this design pattern over a broad range of mobile accelerators by revisiting the usefulness of regular convolutions. We discover that regular convolutions are a potent component to boost the latency-accuracy trade-off for object detection on accelerators, provided that they are placed strategically in the network via neural architecture search. By incorporating regular convolutions in the search space and directly optimizing the network architectures for object detection, we obtain a family of object detection models, MobileDets, that achieve state-of-the-art results across mobile accelerators. On the COCO object detection task, MobileDets outperform MobileNetV3+SSDLite by 1.7 mAP at comparable mobile CPU inference latencies. MobileDets also outperform MobileNetV2+SSDLite by 1.9 mAP on mobile CPUs, 3.7 mAP on Google EdgeTPU, 3.4 mAP on Qualcomm Hexagon DSP and 2.7 mAP on Nvidia Jetson GPU without increasing latency. Moreover, MobileDets are comparable with the state-of-the-art MnasFPN on mobile CPUs even without using the feature pyramid, and achieve better mAP scores on both EdgeTPUs and DSPs with up to 2x speedup. Code and models are available in the TensorFlow Object Detection API: https://github.com/tensorflow/models/tree/master/research/object_detection.