On Neural Architecture Search for Resource-Constrained Hardware Platforms

In the recent past, the success of Neural Architecture Search (NAS) has enabled researchers to broadly explore the design space using learning-based methods. Apart from finding better neural network architectures, the idea of automation has also inspired to improve their implementations on hardware. While some practices of hardware machine-learning automation have achieved remarkable performance, the traditional design concept is still followed: a network architecture is first structured with excellent test accuracy, and then compressed and optimized to fit into a target platform. Such a design flow will easily lead to inferior local-optimal solutions. To address this problem, we propose a new framework to jointly explore the space of neural architecture, hardware implementation, and quantization. Our objective is to find a quantized architecture with the highest accuracy that is implementable on given hardware specifications. We employ FPGAs to implement and test our designs with limited loop-up tables (LUTs) and required throughput. Compared to the separate design/searching methods, our framework has demonstrated much better performance under strict specifications and generated designs of higher accuracy by 18\% to 68\% in the task of classifying CIFAR10 images. With 30,000 LUTs, a light-weight design is found to achieve 82.98\% accuracy and 1293 images/second throughput, compared to which, under the same constraints, the traditional method even fails to find a valid solution.

MSU-Net: Multiscale Statistical U-Net for Real-time 3D Cardiac MRI Video Segmentation

Cardiac magnetic resonance imaging (MRI) is an essential tool for MRI-guided surgery and real-time intervention. The MRI videos are expected to be segmented on-the-fly in real practice. However, existing segmentation methods would suffer from drastic accuracy loss when modified for speedup. In this work, we propose Multiscale Statistical U-Net (MSU-Net) for real-time 3D MRI video segmentation in cardiac surgical guidance. Our idea is to model the input samples as multiscale canonical form distributions for speedup, while the spatio-temporal correlation is still fully utilized. A parallel statistical U-Net is then designed to efficiently process these distributions. The fast data sampling and efficient parallel structure of MSU-Net endorse the fast and accurate inference. Compared with vanilla U-Net and a modified state-of-the-art method GridNet, our method achieves up to 268% and 237% speedup with 1.6% and 3.6% increased Dice scores.

Accurate Congenital Heart Disease Model Generation for 3D Printing

3D printing has been widely adopted for clinical decision making and interventional planning of Congenital heart disease (CHD), while whole heart and great vessel segmentation is the most significant but time-consuming step in the model generation for 3D printing. While various automatic whole heart and great vessel segmentation frameworks have been developed in the literature, they are ineffective when applied to medical images in CHD, which have significant variations in heart structure and great vessel connections. To address the challenge, we leverage the power of deep learning in processing regular structures and that of graph algorithms in dealing with large variations and propose a framework that combines both for whole heart and great vessel segmentation in CHD. Particularly, we first use deep learning to segment the four chambers and myocardium followed by the blood pool, where variations are usually small. We then extract the connection information and apply graph matching to determine the categories of all the vessels. Experimental results using 683D CT images covering 14 types of CHD show that our method can increase Dice score by 11.9% on average compared with the state-of-the-art whole heart and great vessel segmentation method in normal anatomy. The segmentation results are also printed out using 3D printers for validation.

Accurate Congenital Heart Disease ModelGeneration for 3D Printing

3D printing has been widely adopted for clinical decision making and interventional planning of Congenital heart disease (CHD), while whole heart and great vessel segmentation is the most significant but time-consuming step in the model generation for 3D printing. While various automatic whole heart and great vessel segmentation frameworks have been developed in the literature, they are ineffective when applied to medical images in CHD, which have significant variations in heart structure and great vessel connections. To address the challenge, we leverage the power of deep learning in processing regular structures and that of graph algorithms in dealing with large variations and propose a framework that combines both for whole heart and great vessel segmentation in CHD. Particularly, we first use deep learning to segment the four chambers and myocardium followed by bloodpool, where variations are usually small. We then extract the connection information and apply graph matching to determine the categories of all the vessels. Experimental results using 683D CT images covering 14 types of CHD show that our method can increase Dice score by 11.9% on average compared with the state-of-the-art whole heart and great vessel segmentation method in normal anatomy. The segmentation results are also printed out using 3D printers for validation.

Exploiting Computation Power of Blockchain for Biomedical Image Segmentation

Biomedical image segmentation based on Deep neuralnetwork (DNN) is a promising approach that assists clin-ical diagnosis. This approach demands enormous com-putation power because these DNN models are compli-cated, and the size of the training data is usually very huge.As blockchain technology based on Proof-of-Work (PoW)has been widely used, an immense amount of computationpower is consumed to maintain the PoW consensus. Inthis paper, we propose a design to exploit the computationpower of blockchain miners for biomedical image segmen-tation, which lets miners perform image segmentation as theProof-of-Useful-Work (PoUW) instead of calculating use-less hash values. This work distinguishes itself from otherPoUW by addressing various limitations of related others.As the overhead evaluation shown in Section 5 indicates,for U-net and FCN, the average overhead of digital sig-nature is 1.25 seconds and 0.98 seconds, respectively, andthe average overhead of network is 3.77 seconds and 3.01seconds, respectively. These quantitative experiment resultsprove that the overhead of the digital signature and networkis small and comparable to other existing PoUW designs.

Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds

Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It has been demonstrated that for medical images the transmission from local to clouds is much more expensive than the computation in the clouds itself. Towards this, 3D image compression techniques have been widely applied to reduce the data traffic. However, most of the existing image compression techniques are developed around human vision, i.e., they are designed to minimize distortions that can be perceived by human eyes. In this paper we will use deep learning based medical image segmentation as a vehicle and demonstrate that interestingly, machine and human view the compression quality differently. Medical images compressed with good quality w.r.t. human vision may result in inferior segmentation accuracy. We then design a machine vision oriented 3D image compression framework tailored for segmentation using DNNs. Our method automatically extracts and retains image features that are most important to the segmentation. Comprehensive experiments on widely adopted segmentation frameworks with HVSMR 2016 challenge dataset show that our method can achieve significantly higher segmentation accuracy at the same compression rate, or much better compression rate under the same segmentation accuracy, when compared with the existing JPEG 2000 method. To the best of the authors' knowledge, this is the first machine vision guided medical image compression framework for segmentation in the clouds.

SCNN: A General Distribution based Statistical Convolutional Neural Network with Application to Video Object Detection

Various convolutional neural networks (CNNs) were developed recently that achieved accuracy comparable with that of human beings in computer vision tasks such as image recognition, object detection and tracking, etc. Most of these networks, however, process one single frame of image at a time, and may not fully utilize the temporal and contextual correlation typically present in multiple channels of the same image or adjacent frames from a video, thus limiting the achievable throughput. This limitation stems from the fact that existing CNNs operate on deterministic numbers. In this paper, we propose a novel statistical convolutional neural network (SCNN), which extends existing CNN architectures but operates directly on correlated distributions rather than deterministic numbers. By introducing a parameterized canonical model to model correlated data and defining corresponding operations as required for CNN training and inference, we show that SCNN can process multiple frames of correlated images effectively, hence achieving significant speedup over existing CNN models. We use a CNN based video object detection as an example to illustrate the usefulness of the proposed SCNN as a general network model. Experimental results show that even a non-optimized implementation of SCNN can still achieve 178% speedup over existing CNNs with slight accuracy degradation.

On the Quantization of Cellular Neural Networks for Cyber-Physical Systems

Cyber-Physical Systems (CPSs) have been pervasive including smart grid, autonomous automobile systems, medical monitoring, process control systems, robotics systems, and automatic pilot avionics. As usually implemented on embedded devices, CPS is typically constrained by computation capacity and energy consumption. In some CPS applications such as telemedicine and advanced driving assistance system (ADAS), data processing on the embedded devices is preferred due to security/safety and real-time requirement. Therefore, high efficiency is highly desirable for such CPS applications. In this paper we present CeNN quantization for high-efficient processing for CPS applications, particularly telemedicine and ADAS applications. We systematically put forward powers-of-two based incremental quantization of CeNNs for efficient hardware implementation. The incremental quantization contains iterative procedures including parameter partition, parameter quantization, and re-training. We propose five different strategies including random strategy, pruning inspired strategy, weighted pruning inspired strategy, nearest neighbor strategy, and weighted nearest neighbor strategy. Experimental results show that our approach can achieve a speedup up to 7.8x with no performance loss compared with the state-of-the-art FPGA solutions for CeNNs.

A Multi-Resolution Word Embedding for Document Retrieval from Large Unstructured Knowledge Bases

Deep language models learning a hierarchical representation proved to be a powerful tool for natural language processing, text mining and information retrieval. However, representations that perform well for retrieval must capture semantic meaning at different levels of abstraction or context-scopes. In this paper, we propose a new method to generate multi-resolution word embedding representing documents at multiple resolutions in term of context-scopes. In order to investigate its performance, we use the Stanford Question Answering Dataset (SQuAD) and the Question Answering by Search And Reading (QUASAR) in an open-domain question-answering setting, where the first task is to find documents useful for answering a given question. To this end, we first compare the quality of various text-embedding methods for retrieval performance and give an extensive empirical comparison with the performance of various non-augmented base embeddings with and without multi-resolution representation. We argue that multi-resolution word embeddings are consistently superior to the original counterparts and deep residual neural models specifically trained for retrieval purposes can yield further significant gains when they are used for augmenting those embeddings.