Corpus ID: 216868024

MobileDets: Searching for Object Detection Architectures for Mobile Accelerators

@article{Xiong2020MobileDetsSF,
  title={MobileDets: Searching for Object Detection Architectures for Mobile Accelerators},
  author={Yunyang Xiong and Hanxiao Liu and S. Gupta and Berkin Akin and Gabriel Bender and Pieter-Jan Kindermans and Mingxing Tan and V. Singh and B. Chen},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.14525}
}
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 question the optimality of this design pattern over a broad range of mobile accelerators by revisiting the usefulness of regular convolutions. We achieve substantial improvements in the latency-accuracy trade-off by incorporating regular convolutions in the search space, and effectively placing them in… Expand
Filtering Empty Camera Trap Images in Embedded Systems
HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark
  • Chaojian Li, Zhongzhi Yu, +6 authors Yingyan Lin
  • Computer Science
  • ArXiv
  • 2021
Nanopore Base Calling on the Edge
Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
Object Detection Models and Research Directions
  • Zihong Shi
  • 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)
  • 2021
...
1
2
...

References

SHOWING 1-10 OF 46 REFERENCES
MnasFPN: Learning Latency-Aware Pyramid Architecture for Object Detection on Mobile Devices
Pelee: A Real-Time Object Detection System on Mobile Devices
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Searching for MobileNetV3
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
MnasNet: Platform-Aware Neural Architecture Search for Mobile
ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices
  • Zheng Qin, Zeming Li, +4 authors J. Sun
  • Computer Science
  • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
Accelerator-aware Neural Network Design using AutoML
...
1
2
3
4
5
...