InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
Not on the map. Why?
Abstract (arXiv)
The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices. Therefore, we propose InstantNet to automatically generate and deploy instantaneously switchable-precision networks which operate at variable bit-widths. Extensive experiments show that the proposed InstantNet consistently outperforms state-of-the-art designs.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 24 of its 37 references that are in the map. First posted on arXiv 22 Apr 2021.
Builds on
24 of 37 references.
References · 24
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2018DARTS: Differentiable Architecture Searchcited by 1,782
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
- 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
- 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
- 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
- 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 456
- 2018HAQ: Hardware-Aware Automated Quantization with Mixed Precisioncited by 426
- 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 328
- 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 157
12 more
- 2018Scalable Methods for 8-bit Training of Neural Networkscited by 139
- 2018Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Searchcited by 122
- 2019AdaBits: Neural Network Quantization with Adaptive Bit-Widthscited by 63
- 2020AutoGAN-Distiller: Searching to Compress Generative Adversarial Networkscited by 50
- 2019Dual Dynamic Inference: Enabling More Efficient, Adaptive and Controllable Deep Inferencecited by 31
- 2020FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Trainingcited by 23
- 2021CPT: Efficient Deep Neural Network Training via Cyclic Precisioncited by 19
- 2020DNN-Chip Predictor: An Analytical Performance Predictor for DNN Accelerators with Various Dataflows and Hardware Architecturescited by 16
- 2020SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computationcited by 16
- 2018Joint Neural Architecture Search and Quantizationcited by 13
- 2020Switchable Precision Neural Networkscited by 6
- 2018GeneSys: Enabling Continuous Learning through Neural Network Evolution in Hardwarecited by 1
Built on by
Citing papers per year: 2021: 1.
1 paper.