The DOI matches its Crossref record; 30 of the 30 references it cites were found in a registry or an index.
Thin MobileNet: An Enhanced MobileNet Architecture
Abstract
In the field of computer, mobile and embedded vision Convolutional Neural Networks (CNNs) are deep learning models which play a significant role in object detection and recognition. MobileNet is one such efficient, light-weighted model for this purpose, but there are many constraints or challenges for the hardware deployment of such architectures into resource-constrained micro-controller units due to limited memory, energy and power. Also, the overall accuracy of the model generally decreases when the size and the total number of parameters are reduced by any method such as pruning or deep compression. The paper proposes three hybrid MobileNet architectures which has improved accuracy along-with reduced size, lesser number of layers, lower average computation time and very less overfitting as compared to the baseline MobileNet v1. The reason behind developing these models is to have a variant of the existing MobileNet model which will be easily deployable in memory constrained MCUs. We name the model having the smallest size (9.9 MB) as Thin MobileNet. We achieve an increase in accuracy by replacing the standard non-linear activation function ReLU with Drop Activation and introducing Random erasing regularization technique in place of drop out. The model size is reduced by using Separable Convolutions instead of the Depthwise separable convolutions used in the baseline MobileNet. Later on, we make our model shallow by eliminating a few unnecessary layers without a drop in the accuracy. The experimental results are based on training the model on CIFAR-10 dataset.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
(2014) · Cited by 33,419
(2016) · Cited by 31,590
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
Xception: Deep Learning with Depthwise Separable Convolutions
Chollet, F. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.195 · Cited by 20,380
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201
Object Detection With Deep Learning: A Review
Zhao, Z.-Q., Zheng, P., Xu, S.-T., & Wu, X. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2876865 · Cited by 5,545 · cited 1×
“In realtime applications such as image classification [8], captioning [9], object detection [10,23,33] and semantic segmentation [34] in autonomous driving, the inference time and accuracy are very important factors to one's safety.”
BackgroundDeep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1512.03385 · Cited by 4,196
(2013) · Cited by 3,740
Random Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7000 · Cited by 3,617
Random Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2017) · arXiv · doi:10.48550/arxiv.1708.04896 · Cited by 3,617 · cited 3×
“To curb this problem, Random erasing [19] technique was established.”
MethodDeep Learning using Rectified Linear Units (ReLU)
Agarap, A. F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.08375 · Cited by 2,399
Empirical Evaluation of Rectified Activations in Convolutional Network
Xu, B., Wang, N., Chen, T., & Li, M. (2015) · arXiv · doi:10.48550/arxiv.1505.00853 · Cited by 2,264 · cited 2×
“Mathematically speaking, we calculate the expectation of the equation of the standard non-linear function we are using during training, for example, ReLU in this case and get Leaky ReLU [30] with slope (1-”
Method(2013) · Cited by 2,056
Incorporating Nesterov Momentum into Adam
Dozat, T. (2016) · Cited by 1,595
Unsupervised Data Augmentation for Consistency Training
Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1904.12848 · Cited by 1,517
Going Deeper with Convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2014) · arXiv · doi:10.48550/arxiv.1409.4842 · Cited by 1,461 · cited 1×
“Many standard algorithms for computer vision like Canny's algorithm or HOG have been replaced by deep learning models like SqueezeNet [2], SqueezeNext [3], ResNet [4], Inception [5], etc.”
MethodA Comprehensive Survey of Deep Learning for Image Captioning
Hossain, M. Z., Sohel, F., Shiratuddin, M. F., & Laga, H. (2019) · ACM Computing Surveys · doi:10.1145/3295748 · Cited by 879 · cited 1×
“In real-time applications such as image classification [8], captioning [9], object detection [10,23,33] and semantic segmentation [34] in autonomous driving, the inference time and accuracy are very important factors to one's safety.”
BackgroundA-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection
Wang, X., Shrivastava, A., & Gupta, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.324 · Cited by 655
Adaptive dropout for training deep neural networks
Ba, J. L., & Frey, B. J. (2013) · neural information processing systems · Cited by 419
Towards dropout training for convolutional neural networks
Wu, H., & Gu, X. (2015) · Neural Networks · doi:10.1016/j.neunet.2015.07.007 · Cited by 314
Regularization for Deep Learning: A Taxonomy
Kukačka, J., Golkov, V., & Cremers, D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.10686 · Cited by 255
Nesterov's accelerated gradient and momentum as approximations to regularised update descent
Botev, A., Lever, G., & Barber, D. (2017) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7966082 · Cited by 149
SGD Converges to Global Minimum in Deep Learning via Star-convex PathPreprint
Zhou, Y., Yang, J., Zhang, H.-S., Liang, Y.-B., & Tarokh, V. (2019) · International Conference on Learning Representations · doi:10.48550/arxiv.1901.00451 · Cited by 93
Drop-Activation: Implicit Parameter Reduction and Harmonious Regularization
Liang, S., Khoo, Y., & Yang, H. (2020) · Communications on Applied Mathematics and Computation · doi:10.1007/s42967-020-00085-3 · Cited by 26
On Generalization and Regularization in Deep LearningPreprint
Lemberger, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.01312 · Cited by 11
Cited by
Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM
Srinivasu, P. N., SivaSai, J. G., Ijaz, M. F., Bhoi, A. K., Kim, W., & Kang, J. J. (2021) · Sensors · doi:10.3390/s21082852 · Cited by 759
Ali, M. S., Miah, M. S., Haque, J., Rahman, M. M., & Islam, M. K. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100036 · Cited by 415
Gutti, V., & Karthi, R. (2022) · Lecture Notes in Networks and Systems · doi:10.1007/978-3-031-12413-6_27 · Cited by 14
AgCV: An Agentic framework for automating computer vision application
Saxena, A., Chaudhari, A. Y., & Gupta, A. (2025) · MethodsX · doi:10.1016/j.mex.2025.103424 · Cited by 4
Metadata
- Authors
- Sinha, D., & El-Sharkawy, M.
- Venue
- 2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)
- Publisher
- IEEE
- Published
- 2019-10
- Pages
- 0280-0285
- OpenAlex
- W3006086117
- Cited by
- 379
- References
- 30
- FWCI
- 4.39
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.