We present a simple dynamic batching approach applicable to a large class of dynamic architectures that consistently yields speedups of over 10x. We provide performance bounds when the architecture is not known a priori and a stronger bound in the special case where the architecture is a predetermined balanced tree. We evaluate our approach on Johnson et al.'s recent visual question answering (VQA) result of his CLEVR dataset by Inferring and Executing Programs (IEP). We also evaluate on sparsely gated mixture of experts layers and achieve speedups of up to 1000x over the naive implementation.
The University of Sydney（悉尼大学）；BAIDU USA LLC（百度美国有限责任公司）；University of Oxford（牛津大学）；SenseTime Group Limited（商汤科技集团）
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS). BN-NAS can significantly reduce the time required by model training and evaluation in NAS. Specifically, for fast evaluation, we propose a BN-based indicator for predicting subnet performance at a very early training stage. The BN-based indicator further facilitates us to improve the training efficiency by only training the BN parameters during the supernet training. This is based on our observation that training the whole supernet is not necessary while training onl…
Spire Global（斯派尔全球）；Post Luxembourg（卢森堡邮政）；University of Luxembourg（卢森堡大学）
Deep neural networks (DNNs) are typically optimized using various forms of mini-batch gradient descent algorithm. A major motivation for mini-batch gradient descent is that with a suitably chosen batch size, available computing resources can be optimally utilized (including parallelization) for fast model training. However, many works report the progressive loss of model generalization when the training batch size is increased beyond some limits. This is a scenario commonly referred to as generalization gap. Although several works have proposed different methods for alleviating the generalizat…
Convolutional neural networks (CNN) pre-trained on ImageNet are the backbone of most state-of-the-art approaches. In this paper, we present a new set of pre-trained models with popular state-of-the-art architectures for the Caffe framework. The first release includes Residual Networks (ResNets) with generation script as well as the batch-normalization-variants of AlexNet and VGG19. All models outperform previous models with the same architecture. The models and training code are available at http://www.inf-cv.uni-jena.de/Research/CNN+Models.html and https://github.com/cvjena/cnn-models
Dublin City University（都柏林城市大学）；University of Groningen（格罗宁根大学）
Neural handwriting recognition (NHR) is the recognition of handwritten text with deep learning models, such as multi-dimensional long short-term memory (MDLSTM) recurrent neural networks. Models with MDLSTM layers have achieved state-of-the art results on handwritten text recognition tasks. While multi-directional MDLSTM-layers have an unbeaten ability to capture the complete context in all directions, this strength limits the possibilities for parallelization, and therefore comes at a high computational cost. In this work we develop methods to create efficient MDLSTM-based models for NHR, par…
This work investigates the usage of batch normalization in neural architecture search (NAS). Specifically, Frankle et al. find that training BatchNorm only can achieve nontrivial performance. Furthermore, Chen et al. claim that training BatchNorm only can speed up the training of the one-shot NAS supernet over ten times. Critically, there is no effort to understand 1) why training BatchNorm only can find the perform-well architectures with the reduced supernet-training time, and 2) what is the difference between the train-BN-only supernet and the standard-train supernet. We begin by showing th…
Traffic light and sign detectors on autonomous cars are integral for road scene perception. The literature is abundant with deep learning networks that detect either lights or signs, not both, which makes them unsuitable for real-life deployment due to the limited graphics processing unit (GPU) memory and power available on embedded systems. The root cause of this issue is that no public dataset contains both traffic light and sign labels, which leads to difficulties in developing a joint detection framework. We present a deep hierarchical architecture in conjunction with a mini-batch proposal…
Deep Neural Networks (DNNs) are becoming an important tool in modern computing applications. Accelerating their training is a major challenge and techniques range from distributed algorithms to low-level circuit design. In this survey, we describe the problem from a theoretical perspective, followed by approaches for its parallelization. We present trends in DNN architectures and the resulting implications on parallelization strategies. We then review and model the different types of concurrency in DNNs: from the single operator, through parallelism in network inference and training, to distri…
David R. Cheriton School of Computer Science（大卫·R·切里顿计算机科学学院）；University of Waterloo（滑铁卢大学）
Analysis of retinal fundus images is essential for eye-care physicians in the diagnosis, care and treatment of patients. Accurate fundus and/or retinal vessel maps give rise to longitudinal studies able to utilize multimedia image registration and disease/condition status measurements, as well as applications in surgery preparation and biometrics. The segmentation of retinal morphology has numerous applications in assessing ophthalmologic and cardiovascular disease pathologies. The early detection of many such conditions is often the most effective method for reducing patient risk. Computer ai…
The widespread use of Batch Normalization has enabled training deeper neural networks with more stable and faster results. However, the Batch Normalization works best using large batch size during training and as the state-of-the-art segmentation convolutional neural network architectures are very memory demanding, large batch size is often impossible to achieve on current hardware. We evaluate the alternative normalization methods proposed to solve this issue on a problem of binary spine segmentation from 3D CT scan. Our results show the effectiveness of Instance Normalization in the limited …
OPPO Research Institute（OPPO研究院）；Shanghai Jiao Tong University（上海交通大学）
Knowledge distillation (KD) shows a bright promise as a powerful regularization strategy to boost generalization ability by leveraging learned sample-level soft targets. Yet, employing a complex pre-trained teacher network or an ensemble of peer students in existing KD is both time-consuming and computationally costly. Various self KD methods have been proposed to achieve higher distillation efficiency. However, they either require extra network architecture modification or are difficult to parallelize. To cope with these challenges, we propose an efficient and reliable self-distillation frame…
Linnaeus University（林奈大学）；Machine Intelligence Research Labs (MIR Labs)（机器智能研究实验室）
Deep learning is an important component of big-data analytic tools and intelligent applications, such as, self-driving cars, computer vision, speech recognition, or precision medicine. However, the training process is computationally intensive, and often requires a large amount of time if performed sequentially. Modern parallel computing systems provide the capability to reduce the required training time of deep neural networks. In this paper, we present our parallelization scheme for training convolutional neural networks (CNN) named Controlled Hogwild with Arbitrary Order of Synchronization …
A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep architectures, it has been challenging both to generically improve upon Batch Normalization and to understand the circumstances that lend themselves to other enhancements. In this paper, we identify four improvements to the generic form of Batch Normalization and the circumstances under which they work, yielding performance gains across all batch sizes while requiring no additional computation during training. These co…
Batch Normalization (BN) uses mini-batch statistics to normalize the activations during training, introducing dependence between mini-batch elements. This dependency can hurt the performance if the mini-batch size is too small, or if the elements are correlated. Several alternatives, such as Batch Renormalization and Group Normalization (GN), have been proposed to address this issue. However, they either do not match the performance of BN for large batches, or still exhibit degradation in performance for smaller batches, or introduce artificial constraints on the model architecture. In this pa…
We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learning architecture on a fine-grained-level. Individual convolutional maps are turned on/off conditionally on features in the network. To achieve this, we introduce a new residual block architecture that gates convolutional channels in a fine-grained manner. We also introduce a generally applicable tool $batch$-$shaping$ that matches the marginal aggregate posteriors of features in a neural network to a pre-specified prio…
Arizona State University（亚利桑那州立大学）；Nanyang Technological University（南洋理工大学）
FPGA-based hardware accelerators for convolutional neural networks (CNNs) have obtained great attentions due to their higher energy efficiency than GPUs. However, it is challenging for FPGA-based solutions to achieve a higher throughput than GPU counterparts. In this paper, we demonstrate that FPGA acceleration can be a superior solution in terms of both throughput and energy efficiency when a CNN is trained with binary constraints on weights and activations. Specifically, we propose an optimized FPGA accelerator architecture tailored for bitwise convolution and normalization that features mas…
Melanoma, one of most dangerous types of skin cancer, re-sults in a very high mortality rate. Early detection and resection are two key points for a successful cure. Recent research has used artificial intelligence to classify melanoma and nevus and to compare the assessment of these algorithms to that of dermatologists. However, an imbalance of sensitivity and specificity measures affected the performance of existing models. This study proposes a method using deep convolutional neural networks aiming to detect melanoma as a binary classification problem. It involves 3 key features, namely cus…
