MobileNetV2: Inverted Residuals and Linear Bottlenecks. In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3. The MobileNetV2 architecture is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers opposite to traditional residual models which use expanded representations in the input an MobileNetV2 uses lightweight depthwise convolutions to filter features in the intermediate expansion layer. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on Imagenet classification, COCO object detection, VOC image segmentation. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as the number of parameters

References in zbMATH (referenced in 17 articles )

Showing results 1 to 17 of 17.
Sorted by year (citations)

  1. Roslidar, Roslidar; Syaryadhi, Mohd; Saddami, Khairun; Pradhan, Biswajeet; Arnia, Fitri; Syukri, Maimun; Munadi, Khairul: BreaCNet: a high-accuracy breast thermogram classifier based on mobile convolutional neural network (2022)
  2. Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang: BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search (2021) arXiv
  3. Liu, Chunlei; Ding, Wenrui; Hu, Yuan; Zhang, Baochang; Liu, Jianzhuang; Guo, Guodong; Doermann, David: Rectified binary convolutional networks with generative adversarial learning (2021)
  4. Toğaçar, Mesut; Cömert, Zafer; Ergen, Burhan: Intelligent skin cancer detection applying autoencoder, MobileNetV2 and spiking neural networks (2021)
  5. Toğaçar, Mesut; Cömert, Zafer; Ergen, Burhan: Corrigendum to “Intelligent skin cancer detection applying autoencoder, MobileNetV2 and spiking neural networks” (2021)
  6. Truong, Tuyen Trung; Nguyen, Hang-Tuan: Backtracking gradient descent method and some applications in large scale optimisation. II: Algorithms and experiments (2021)
  7. Wu, Zhenni; Chen, Hengxin; Fang, Bin; Li, Zihao; Chen, Xinrun: Building pose estimation from the perspective of UAVs based on CNNs (2021)
  8. Xie, Qiyang; Wang, Xingrui; Sun, Hongyu; Zhang, Yongtao; Lu, Xiang: ECG signal detection and classification of heart rhythm diseases based on ResNet and LSTM (2021)
  9. Yang, Hongfei; Ding, Xiaofeng; Chan, Raymond; Hu, Hui; Peng, Yaxin; Zeng, Tieyong: A new initialization method based on normed statistical spaces in deep networks (2021)
  10. Amosov, O. S.; Amosova, S. G.; Zhiganov, S. V.; Ivanov, Yu. S.; Pashchenko, F. F.: Computational method for recognizing situations and objects in the frames of a continuous video stream using deep neural networks for access control systems (2020)
  11. Chen Gao, Yunpeng Chen, Si Liu, Zhenxiong Tan, Shuicheng Yan: AdversarialNAS: Adversarial Neural Architecture Search for GANs (2020) arXiv
  12. Gao, Jing; Li, Peng; Chen, Zhikui; Zhang, Jianing: A survey on deep learning for multimodal data fusion (2020)
  13. Kang, Dongseok; Ahn, Chang Wook: Efficient neural network space with genetic search (2020)
  14. Kumar, Kamlesh; Saeed, Umair; Rai, Athaul; Islam, Noman; Shaikh, Ghulam Muhammad; Qayoom, Abdul: IDC breast cancer detection using deep learning schemes (2020)
  15. Sharma, Vipul; Mir, Roohie Naaz: A comprehensive and systematic look up into deep learning based object detection techniques: a review (2020)
  16. Valada, Abhinav; Mohan, Rohit; Burgard, Wolfram: Self-supervised model adaptation for multimodal semantic segmentation (2020)
  17. Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang: DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better (2019) arXiv