scispace - formally typeset
Search or ask a question
Topic

Mobile architecture

About: Mobile architecture is a research topic. Over the lifetime, 266 publications have been published within this topic receiving 14019 citations.


Papers
More filters
Proceedings ArticleDOI
Mark Sandler1, Andrew Howard1, Menglong Zhu1, Andrey Zhmoginov1, Liang-Chieh Chen1 
18 Jun 2018
TL;DR: MobileNetV2 as mentioned in this paper is based on an inverted residual structure where the shortcut connections are between the thin bottleneck layers and intermediate expansion layer uses lightweight depthwise convolutions to filter features as a source of non-linearity.
Abstract: 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. is based on an inverted residual structure where the shortcut connections are between the thin bottleneck layers. The intermediate expansion layer uses lightweight depthwise convolutions to filter features as a source of non-linearity. 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 [1] classification, COCO object detection [2], VOC image segmentation [3]. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as actual latency, and the number of parameters.

9,381 citations

Posted Content
Mark Sandler1, Andrew Howard1, Menglong Zhu1, Andrey Zhmoginov1, Liang-Chieh Chen1 
TL;DR: A new mobile architecture, MobileNetV2, is described 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 and allows decoupling of the input/output domains from the expressiveness of the transformation.
Abstract: 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

8,807 citations

Posted Content
13 Jan 2018
TL;DR: 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 is described.
Abstract: 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

680 citations

Proceedings ArticleDOI
06 Jun 2004
TL;DR: It is found that the active mobile architecture performs better at tracking, but that the passive mobile architecture has acceptable performance; moreover, a hybrid approach is devised that preserves the benefits of the Passive mobile architecture while simultaneously providing the same performance as an active mobile system.
Abstract: We study the problem of tracking a moving device under two indoor location architectures: an active mobile architecture and a passive mobile architecture. In the former, the infrastructure has receivers at known locations, which estimate distances to a mobile device based on an active transmission from the device. In the latter, the infrastructure has active beacons that periodically transmit signals to a passively listening mobile device, which in turn estimates distances to the beacons. Because the active mobile architecture receives simultaneous distance estimates at multiple receivers from the mobile device, it is likely to perform better tracking than the passive mobile system in which the device obtains only one distance estimate at a time and may have moved between successive estimates. However, an passive mobile system scales better with the number of mobile devices and puts users in control of whether their whereabouts are tracked.We answer the following question: How do the two architectures compare in tracking performance? We find that the active mobile architecture performs better at tracking, but that the passive mobile architecture has acceptable performance; moreover, we devise a hybrid approach that preserves the benefits of the passive mobile architecture while simultaneously providing the same performance as an active mobile system, suggesting a viable practical solution to the three goals of scalability, privacy, and tracking agility.

458 citations

Proceedings ArticleDOI
12 Dec 2009
TL;DR: A regression-based power estimation model is presented that accurately estimates power consumption and provides insights about the power breakdown among hardware components, and it is shown that energy consumption widely varies depending upon the user.
Abstract: As the market for mobile architectures continues its rapid growth, it has become increasingly important to understand and optimize the power consumption of these battery-driven devices. While energy consumption has been heavily explored, there is one critical factor that is often overlooked -- the end user. Ultimately, the energy consumption of a mobile architecture is defined by user activity. In this paper, we study mobile architectures in their natural environment -- in the hands of the end user. Specifically, we develop a logger application for Android G1 mobile phones and release the logger into the wild to collect traces of real user activity. We then show how the traces can be used to characterize power consumption, and guide the development of power optimizations. We present a regression-based power estimation model that only relies on easily-accessible measurements collected by our logger. The model accurately estimates power consumption and provides insights about the power breakdown among hardware components. We show that energy consumption widely varies depending upon the user. In addition, our results show that the screen and the CPU are the two largest power consuming components. We also study patterns in user behavior to derive power optimizations. We observe that majority of the active screen time is dominated by long screen intervals. To reduce the energy consumption during these long intervals, we implement a scheme that slowly reduces the screen brightness over time. Our results reveal that the users are happier with a system that slowly reduces the screen brightness rather than abruptly doing so, even though the two schemes settle at the same brightness. Similarly, we experiment with a scheme that slowly reduces the CPU frequency over time. We evaluate these optimizations with a user study and demonstrate 10.6% total system energy savings with a minimal impact on user satisfaction.

397 citations


Network Information
Related Topics (5)
Server
79.5K papers, 1.4M citations
77% related
User interface
85.4K papers, 1.7M citations
75% related
Wireless sensor network
142K papers, 2.4M citations
74% related
Wireless
133.4K papers, 1.9M citations
72% related
Wireless network
122.5K papers, 2.1M citations
72% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20221
20214
20204
201910
201813
201711