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 [12] on ImageNet classification task, under the computation budget of 40 MFLOPs. On an ARM-based mobile device, ShuffleNet achieves ~13A— actual speedup over AlexNet while maintaining comparable accuracy.

/pdf/shufflenet-an-extremely-efficient-convolutional-neural-1ptfqz7r4g.pdf

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

Recent advances in convolutional neural networks

In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction. We further generalize this algorithm to multi-layer and multi-branch cases. Our method reduces the accumulated error and enhance the compatibility with various architectures. Our pruned VGG-16 achieves the state-of-the-art results by 5× speed-up along with only 0.3% increase of error. More importantly, our method is able to accelerate modern networks like ResNet, Xception and suffers only 1.4%, 1.0% accuracy loss under 2× speedup respectively, which is significant.

Channel Pruning for Accelerating Very Deep Neural Networks

The success of deep learning in vision can be attributed to: (a) models with high capacity; (b) increased computational power; and (c) availability of large-scale labeled data. Since 2012, there have been significant advances in representation capabilities of the models and computational capabilities of GPUs. But the size of the biggest dataset has surprisingly remained constant. What will happen if we increase the dataset size by 10 × or 100 × ? This paper takes a step towards clearing the clouds of mystery surrounding the relationship between ‘enormous data’ and visual deep learning. By exploiting the JFT-300M dataset which has more than 375M noisy labels for 300M images, we investigate how the performance of current vision tasks would change if this data was used for representation learning. Our paper delivers some surprising (and some expected) findings. First, we find that the performance on vision tasks increases logarithmically based on volume of training data size. Second, we show that representation learning (or pre-training) still holds a lot of promise. One can improve performance on many vision tasks by just training a better base model. Finally, as expected, we present new state-of-the-art results for different vision tasks including image classification, object detection, semantic segmentation and human pose estimation. Our sincere hope is that this inspires vision community to not undervalue the data and develop collective efforts in building larger datasets.

Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

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.

Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in automatic translation, speech-to-text, scene understanding, ranking user preferences, ad placement, etc Competing frameworks for building these networks such as TensorFlow, Chainer, CNTK, Torch/PyTorch, Caffe1/2, MXNet and Theano, explore different tradeoffs between usability and expressiveness, research or production orientation and supported hardware They operate on a DAG of computational operators, wrapping high-performance libraries such as CUDNN (for NVIDIA GPUs) or NNPACK (for various CPUs), and automate memory allocation, synchronization, distribution Custom operators are needed where the computation does not fit existing high-performance library calls, usually at a high engineering cost This is frequently required when new operators are invented by researchers: such operators suffer a severe performance penalty, which limits the pace of innovation Furthermore, even if there is an existing runtime call these frameworks can use, it often doesn't offer optimal performance for a user's particular network architecture and dataset, missing optimizations between operators as well as optimizations that can be done knowing the size and shape of data Our contributions include (1) a language close to the mathematics of deep learning called Tensor Comprehensions, (2) a polyhedral Just-In-Time compiler to convert a mathematical description of a deep learning DAG into a CUDA kernel with delegated memory management and synchronization, also providing optimizations such as operator fusion and specialization for specific sizes, (3) a compilation cache populated by an autotuner [Abstract cutoff]

Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions

We examine the performance profile of Convolutional Neural Network training on the current generation of NVIDIA Graphics Processing Units. We introduce two new Fast Fourier Transform convolution implementations: one based on NVIDIA's cuFFT library, and another based on a Facebook authored FFT implementation, fbfft, that provides significant speedups over cuFFT (over 1.5x) for whole CNNs. Both of these convolution implementations are available in open source, and are faster than NVIDIA's cuDNN implementation for many common convolutional layers (up to 23.5x for some synthetic kernel configurations). We discuss different performance regimes of convolutions, comparing areas where straightforward time domain convolutions outperform Fourier frequency domain convolutions. Details on algorithmic applications of NVIDIA GPU hardware specifics in the implementation of fbfft are also provided.

Fast Convolutional Nets With fbfft: A GPU Performance Evaluation

Modern compilers are responsible for translating the idealistic operational semantics of the source program into a form that makes efficient use of a highly complex heterogeneous machine. Since optimization problems are associated with huge and unstructured search spaces, this combinational task is poorly achieved in general, resulting in weak scalability and disappointing sustained performance. We address this challenge by working on the program representation itself, using a semi-automatic optimization approach to demonstrate that current compilers offen suffer from unnecessary constraints and intricacies that can be avoided in a semantically richer transformation framework. Technically, the purpose of this paper is threefold: (1) to show that syntactic code representations close to the operational semantics lead to rigid phase ordering and cumbersome expression of architecture-aware loop transformations, (2) to illustrate how complex transformation sequences may be needed to achieve significant performance benefits, (3) to facilitate the automatic search for program transformation sequences, improving on classical polyhedral representations to better support operation research strategies in a simpler, structured search space. The proposed framework relies on a unified polyhedral representation of loops and statements, using normalization rules to allow flexible and expressive transformation sequencing. This representation allows to extend the scalability of polyhedral dependence analysis, and to delay the (automatic) legality checks until the end of a transformation sequence. Our work leverages on algorithmic advances in polyhedral code generation and has been implemented in a modern research compiler.

/pdf/semi-automatic-composition-of-loop-transformations-for-deep-ktssmubyud.pdf

Semi-automatic composition of loop transformations for deep parallelism and memory hierarchies

Convolutional networks trained on large supervised dataset produce visual features which form the basis for the state-of-the-art in many computer-vision problems. Further improvements of these visual features will likely require even larger manually labeled data sets, which severely limits the pace at which progress can be made. In this paper, we explore the potential of leveraging massive, weakly-labeled image collections for learning good visual features. We train convolutional networks on a dataset of 100 million Flickr photos and captions, and show that these networks produce features that perform well in a range of vision problems. We also show that the networks appropriately capture word similarity, and learn correspondences between different languages.

Learning Visual Features from Large Weakly Supervised Data

Convolutional networks trained on large supervised datasets produce visual features which form the basis for the state-of-the-art in many computer-vision problems. Further improvements of these visual features will likely require even larger manually labeled data sets, which severely limits the pace at which progress can be made. In this paper, we explore the potential of leveraging massive, weakly-labeled image collections for learning good visual features. We train convolutional networks on a dataset of 100 million Flickr photos and comments, and show that these networks produce features that perform well in a range of vision problems. We also show that the networks appropriately capture word similarity and learn correspondences between different languages.

/pdf/learning-visual-features-from-large-weakly-supervised-data-1nkcg0ran0.pdf

Nicolas Vasilache

Papers

Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions

Fast Convolutional Nets With fbfft: A GPU Performance Evaluation

Semi-automatic composition of loop transformations for deep parallelism and memory hierarchies

Learning Visual Features from Large Weakly Supervised Data

Learning Visual Features from Large Weakly Supervised Data