MobileNetV2: Inverted Residuals and Linear Bottlenecks

Sandler, Mark; Howard, Andrew; Zhu, Menglong; Zhmoginov, Andrey; Chen, Liang-Chieh

doi:10.48550/arxiv.1801.04381

Cited by 444 publications

(306 citation statements)

References 20 publications

Supporting

Mentioning

220

Contrasting

Unclassified

Order By: Relevance

“…For classification, three pre-trained CNN models were used ResNet18 [35], MobileNet_V2 [36], and EfficientNet_B1 [37] and for semantic segmentation of hand region and background removal, three CNN models such as DenseNet201 Feature Pyramid Networks (FPN) [38], U-Net [39], and M-UNet [40] were used.…”

Section: Classification and Segmentation Modelsmentioning

confidence: 99%

“…[35] provided evidence of vanishing gradients and decreasing accuracy after saturation. MobileNet_V2 [36] was designed to replace expensive convolution networks with a cheaper network. Ref.…”

Section: Classification and Segmentation Modelsmentioning

confidence: 99%

“…Ref. [36] implemented expansion/projection layers and residual connections to make this network usable in mobile devices. It is also mentioned that removing nonlinearities in narrow layers is important for maintaining representational power.…”

Section: Classification and Segmentation Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model

Podder

Chowdhury

Tahir

et al. 2022

Sensors

View full text Add to dashboard Cite

A real-time Bangla Sign Language interpreter can enable more than 200 k hearing and speech-impaired people to the mainstream workforce in Bangladesh. Bangla Sign Language (BdSL) recognition and detection is a challenging topic in computer vision and deep learning research because sign language recognition accuracy may vary on the skin tone, hand orientation, and background. This research has used deep machine learning models for accurate and reliable BdSL Alphabets and Numerals using two well-suited and robust datasets. The dataset prepared in this study comprises of the largest image database for BdSL Alphabets and Numerals in order to reduce inter-class similarity while dealing with diverse image data, which comprises various backgrounds and skin tones. The papers compared classification with and without background images to determine the best working model for BdSL Alphabets and Numerals interpretation. The CNN model trained with the images that had a background was found to be more effective than without background. The hand detection portion in the segmentation approach must be more accurate in the hand detection process to boost the overall accuracy in the sign recognition. It was found that ResNet18 performed best with 99.99% accuracy, precision, F1 score, sensitivity, and 100% specificity, which outperforms the works in the literature for BdSL Alphabets and Numerals recognition. This dataset is made publicly available for researchers to support and encourage further research on Bangla Sign Language Interpretation so that the hearing and speech-impaired individuals can benefit from this research.

show abstract

Section: Classification and Segmentation Modelsmentioning

confidence: 99%

Section: Classification and Segmentation Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model

Podder

Chowdhury

Tahir

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Yolo v3 [47] TensorFlow v2 TinyYolo v3 [47] TensorFlow v2 MobileNet SSD v2 [48] Coral TPU Face recognition VGGFace (Senet50) [14] TensorFlow v1…”

Section: Image Classificationunclassified

SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge Devices

Min,

Mathur,

Acer

et al. 2021

Preprint

View full text Add to dashboard Cite

We present SensiX++ -a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors. SensiX++ operates on two fundamental principles -highly modular componentisation to externalise data operations with clear abstractions and document-centric manifestation for system-wide orchestration. First, a data coordinator manages the lifecycle of sensors and serves models with correct data through automated transformations. Next, a resource-aware model server executes multiple models in isolation through model abstraction, pipeline automation and feature sharing. An adaptive scheduler then orchestrates the best-effort executions of multiple models across heterogeneous accelerators, balancing latency and throughput. Finally, microservices with REST APIs serve synthesised model predictions, system statistics, and continuous deployment. Collectively, these components enable SensiX++ to serve multiple models efficiently with fine-grained control on edge devices while minimising data operation redundancy, managing data and device heterogeneity, reducing resource contention and removing manual MLOps. We benchmark SensiX++ with ten different vision and acoustics models across various multi-tenant configurations on different edge accelerators (Jetson AGX and Coral TPU) designed for sensory devices. We report on the overall throughput and quantified benefits of various automation components of SensiX++ and demonstrate its efficacy to significantly reduce operational complexity and lower the effort to deploy, upgrade, reconfigure and serve embedded models on edge devices.

show abstract

“…State-or-the-art performance are achieved by designing wider and deeper CNNs [41,13,18]. However, the over-parameterization problem of CNNs prevents them from being applied to resource-limited devices, such as mobile phones and robotics [39,32]. Many approaches have been proposed to reduce the computation and storage cost of CNNs, such as quantization [10], matrix decomposition [48], network pruning [11,24,46,44,15], and knowledge distillation [16].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Neural Network Pruning with Structural Redundancy Reduction

Wang¹,

Li²,

Wang³

2021

Preprint

View full text Add to dashboard Cite

Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to achieve compact architectures. In this study, we claim that identifying structural redundancy plays a more essential role than finding unimportant filters, theoretically and empirically. We first statistically model the network pruning problem in a redundancy reduction perspective and find that pruning in the layer(s) with the most structural redundancy outperforms pruning the least important filters across all layers. Based on this finding, we then propose a network pruning approach that identifies structural redundancy of a CNN and prunes filters in the selected layer(s) with the most redundancy. Experiments on various benchmark network architectures and datasets show that our proposed approach significantly outperforms the previous state-of-the-art.

show abstract

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Cited by 444 publications

References 20 publications

Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model

Bangla Sign Language (BdSL) Alphabets and Numerals Classification Using a Deep Learning Model

SensiX++: Bringing MLOPs and Multi-tenant Model Serving to Sensory Edge Devices

Convolutional Neural Network Pruning with Structural Redundancy Reduction

Contact Info

Product

Resources

About