MnasNet is a type of convolutional neural network optimized for mobile advices that is discovered through mobile neural architecture search, which explicitly incorporates model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. The main building block is a inverted residual block (from MobileNetV2).

Source: MnasNet: Platform-Aware Neural Architecture Search for Mobile

Latest Papers

PAPER DATE
EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search
| Ching-Chen WangChing-Te ChiuJheng-Yi Chang
2020-09-16
Leveraging Automated Mixed-Low-Precision Quantization for tiny edge microcontrollers
Manuele RusciMarco FariselliAlessandro CapotondiLuca Benini
2020-08-12
To filter prune, or to layer prune, that is the question
Sara ElkerdawyMostafa ElhoushiAbhineet SinghHong ZhangNilanjan Ray
2020-07-11
Fine-Grained Stochastic Architecture Search
| Shraman Ray ChaudhuriElad EbanHanhan LiMax MorozYair Movshovitz-Attias
2020-06-17
Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
Chunjie LuoXiwen HeJianfeng ZhanLei WangWanling GaoJiahui Dai
2020-05-07
Neural Epitome Search for Architecture-Agnostic Network Compression
Daquan ZhouXiaojie JinQibin HouKaixin WangJianchao YangJiashi Feng
2019-07-12
Attention Augmented Convolutional Networks
| Irwan BelloBarret ZophAshish VaswaniJonathon ShlensQuoc V. Le
2019-04-22
CondConv: Conditionally Parameterized Convolutions for Efficient Inference
| Brandon YangGabriel BenderQuoc V. LeJiquan Ngiam
2019-04-10
AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
| Jiahui YuThomas Huang
2019-03-27
ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
| Xiaoliang DaiPeizhao ZhangBichen WuHongxu YinFei SunYanghan WangMarat DukhanYunqing HuYiming WuYangqing JiaPeter VajdaMatt UyttendaeleNiraj K. Jha
2018-12-21
MnasNet: Platform-Aware Neural Architecture Search for Mobile
| Mingxing TanBo ChenRuoming PangVijay VasudevanMark SandlerAndrew HowardQuoc V. Le
2018-07-31

Tasks

TASK PAPERS SHARE
Object Detection 4 44.44%
Image Classification 3 33.33%
Quantization 1 11.11%
Model Compression 1 11.11%

Categories