NoNN partitions a teacher model into disjoint compressed students via network science for distributed IoT inference, matching teacher accuracy with far lower per-device memory and communication.
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices.arXiv 2017
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The new architecture utilizes two new operations, pointwise group convolution and channel shuffle, to greatly reduce computation cost while maintaining accuracy. Experiments on ImageNet classification and MS COCO object detection demonstrate the superior performance of ShuffleNet over other structures, e.g. lower top-1 error (absolute 7.8%) than recent MobileNet on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13x actual speedup over AlexNet while maintaining comparable accuracy.
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
A co-evolutionary compression technique reduces parameters and FLOPs in unpaired image-to-image translation GAN generators while maintaining translation quality on benchmarks.
EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.
Replacing pointwise convolutions with DWHT yields a model with 79.1% fewer parameters, 48.4% fewer FLOPs, and 1.49% higher accuracy than MobileNet-V1 on CIFAR-100.
Empirical comparison of transfer learning performance across eleven pre-trained models on five image datasets using accuracy, time, and size metrics.
citing papers explorer
-
Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT
NoNN partitions a teacher model into disjoint compressed students via network science for distributed IoT inference, matching teacher accuracy with far lower per-device memory and communication.
-
Co-Evolutionary Compression for Unpaired Image Translation
A co-evolutionary compression technique reduces parameters and FLOPs in unpaired image-to-image translation GAN generators while maintaining translation quality on benchmarks.
-
EPNAS: Efficient Progressive Neural Architecture Search
EPNAS uses a progressive search policy with REINFORCE performance prediction to search neural architectures in parallel, supporting multiple resource constraints and outperforming ENAS and PNAS on CIFAR-10 and ImageNet in speed and accuracy.
-
New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms
Replacing pointwise convolutions with DWHT yields a model with 79.1% fewer parameters, 48.4% fewer FLOPs, and 1.49% higher accuracy than MobileNet-V1 on CIFAR-100.
-
A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
Empirical comparison of transfer learning performance across eleven pre-trained models on five image datasets using accuracy, time, and size metrics.