Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). 
The SqueezeNet architecture is available for download here: this https URL

/pdf/squeezenet-alexnet-level-accuracy-with-50x-fewer-parameters-175af9qwgu.pdf

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets. While custom hardware helps the computation, fetching weights from DRAM is two orders of magnitude more expensive than ALU operations, and dominates the required power.Previously proposed 'Deep Compression' makes it possible to fit large DNNs (AlexNet and VGGNet) fully in on-chip SRAM. This compression is achieved by pruning the redundant connections and having multiple connections share the same weight. We propose an energy efficient inference engine (EIE) that performs inference on this compressed network model and accelerates the resulting sparse matrix-vector multiplication with weight sharing. Going from DRAM to SRAM gives EIE 120× energy saving; Exploiting sparsity saves 10×; Weight sharing gives 8×; Skipping zero activations from ReLU saves another 3×. Evaluated on nine DNN benchmarks, EIE is 189× and 13× faster when compared to CPU and GPU implementations of the same DNN without compression. EIE has a processing power of 102 GOPS working directly on a compressed network, corresponding to 3 TOPS on an uncompressed network, and processes FC layers of AlexNet at 1.88×104 frames/sec with a power dissipation of only 600mW. It is 24,000× and 3,400× more energy efficient than a CPU and GPU respectively. Compared with DaDianNao, EIE has 2.9×, 19× and 3× better throughput, energy efficiency and area efficiency.

EIE: efficient inference engine on compressed deep neural network

Convolutional neural networks CNNs have been applied to visual tasks since the late 1980s. However, despite a few scattered applications, they were dormant until the mid-2000s when developments in computing power and the advent of large amounts of labeled data, supplemented by improved algorithms, contributed to their advancement and brought them to the forefront of a neural network renaissance that has seen rapid progression since 2012. In this review, which focuses on the application of CNNs to image classification tasks, we cover their development, from their predecessors up to recent state-of-the-art deep learning systems. Along the way, we analyze 1 their early successes, 2 their role in the deep learning renaissance, 3 selected symbolic works that have contributed to their recent popularity, and 4 several improvement attempts by reviewing contributions and challenges of over 300 publications. We also introduce some of their current trends and remaining challenges.

Deep convolutional neural networks for image classification: A comprehensive review

Machine learning is enabling a myriad innovations, including new algorithms for cancer diagnosis and self-driving cars. The broad use of machine learning makes it important to understand the extent to which machine-learning algorithms are subject to attack, particularly when used in applications where physical security or safety is at risk. In this paper, we focus on facial biometric systems, which are widely used in surveillance and access control. We define and investigate a novel class of attacks: attacks that are physically realizable and inconspicuous, and allow an attacker to evade recognition or impersonate another individual. We develop a systematic method to automatically generate such attacks, which are realized through printing a pair of eyeglass frames. When worn by the attacker whose image is supplied to a state-of-the-art face-recognition algorithm, the eyeglasses allow her to evade being recognized or to impersonate another individual. Our investigation focuses on white-box face-recognition systems, but we also demonstrate how similar techniques can be used in black-box scenarios, as well as to avoid face detection.

https://dl.acm.org/doi/pdf/10.1145/2976749.2978392

Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams \emph{in parallel}; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at~{\url{this https URL}}.

Deep High-Resolution Representation Learning for Visual Recognition

In recent years, convolutional neural network (CNN) based methods have achieved great success in a large number of applications and have been among the most powerful and widely used techniques in computer vision. However, CNN-based methods are com-putational-intensive and resource-consuming, and thus are hard to be integrated into embedded systems such as smart phones, smart glasses, and robots. FPGA is one of the most promising platforms for accelerating CNN, but the limited bandwidth and on-chip memory size limit the performance of FPGA accelerator for CNN.In this paper, we go deeper with the embedded FPGA platform on accelerating CNNs and propose a CNN accelerator design on embedded FPGA for Image-Net large-scale image classification. We first present an in-depth analysis of state-of-the-art CNN models and show that Convolutional layers are computational-centric and Fully-Connected layers are memory-centric.Then the dynamic-precision data quantization method and a convolver design that is efficient for all layer types in CNN are proposed to improve the bandwidth and resource utilization. Results show that only 0.4% accuracy loss is introduced by our data quantization flow for the very deep VGG16 model when 8/4-bit quantization is used. A data arrangement method is proposed to further ensure a high utilization of the external memory bandwidth. Finally, a state-of-the-art CNN, VGG16-SVD, is implemented on an embedded FPGA platform as a case study. VGG16-SVD is the largest and most accurate network that has been implemented on FPGA end-to-end so far. The system on Xilinx Zynq ZC706 board achieves a frame rate at 4.45 fps with the top-5 accuracy of 86.66% using 16-bit quantization. The average performance of convolutional layers and the full CNN is 187.8 GOP/s and 137.0 GOP/s under 150MHz working frequency, which outperform previous approaches significantly.

Going Deeper with Embedded FPGA Platform for Convolutional Neural Network

We present a new approach to localize extensive facial landmarks with a coarse-to-fine convolutional network cascade. Deep convolutional neural networks (DCNN) have been successfully utilized in facial landmark localization for two-fold advantages: 1) geometric constraints among facial points are implicitly utilized, 2) huge amount of training data can be leveraged. However, in the task of extensive facial landmark localization, a large number of facial landmarks (more than 50 points) are required to be located in a unified system, which poses great difficulty in the structure design and training process of traditional convolutional networks. In this paper, we design a four-level convolutional network cascade, which tackles the problem in a coarse-to-fine manner. In our system, each network level is trained to locally refine a subset of facial landmarks generated by previous network levels. In addition, each level predicts explicit geometric constraints (the position and rotation angles of a specific facial component) to rectify the inputs of the current network level. The combination of coarse-to-fine cascade and geometric refinement enables our system to locate extensive facial landmarks (68 points) accurately in the 300-W facial landmark localization challenge.

/pdf/extensive-facial-landmark-localization-with-coarse-to-fine-2djthfzk94.pdf

Extensive Facial Landmark Localization with Coarse-to-Fine Convolutional Network Cascade

Face recognition performance improves rapidly with the recent deep learning
technique developing and underlying large training dataset accumulating. In
this paper, we report our observations on how big data impacts the recognition
performance. According to these observations, we build our Megvii Face
Recognition System, which achieves 99.50% accuracy on the LFW benchmark,
outperforming the previous state-of-the-art. Furthermore, we report the
performance in a real-world security certification scenario. There still exists
a clear gap between machine recognition and human performance. We summarize our
experiments and present three challenges lying ahead in recent face
recognition. And we indicate several possible solutions towards these
challenges. We hope our work will stimulate the community's discussion of the
difference between research benchmark and real-world applications.

/pdf/naive-deep-face-recognition-touching-the-limit-of-lfw-4qr0rg8lqi.pdf

Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?

Face hallucination method is proposed to generate high-resolution images from low-resolution ones for better visualization. However, conventional hallucination methods are often designed for controlled settings and cannot handle varying conditions of pose, resolution degree, and blur. In this paper, we present a new method of face hallucination, which can consistently improve the resolution of face images even with large appearance variations. Our method is based on a novel network architecture called Bi-channel Convolutional Neural Network (Bi-channel CNN). It extracts robust face representations from raw input by using deep convolu-tional network, then adaptively integrates two channels of information (the raw input image and face representations) to predict the high-resolution image. Experimental results show our system outperforms the prior state-of-the-art methods.

https://www.aaai.org/ocs/index.php/AAAI/AAAI15/paper/viewFile/9752/9824

Erjin Zhou

Papers

Going Deeper with Embedded FPGA Platform for Convolutional Neural Network

Extensive Facial Landmark Localization with Coarse-to-Fine Convolutional Network Cascade

Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?

Learning face hallucination in the wild

Approaching human level facial landmark localization by deep learning