Accurate pedestrian detection has a primary role in automotive safety: for example, by issuing warnings to the driver or acting actively on car's brakes, it helps decreasing the probability of injuries and human fatalities. In order to achieve very high accuracy, recent pedestrian detectors have been based on Convolutional Neural Networks (CNN). Unfortunately, such approaches require vast amounts of computational power and memory, preventing efficient implementations on embedded systems. This work proposes a CNN-based detector, adapting a general-purpose convolutional network to the task at hand. By thoroughly analyzing and optimizing each step of the detection pipeline, we develop an architecture that outperforms methods based on traditional image features and achieves an accuracy close to the state-of-the-art while having low computational complexity. Furthermore, the model is compressed in order to fit the tight constrains of low power devices with a limited amount of embedded memory available. This paper makes two main contributions: (1) it proves that a region based deep neural network can be finely tuned to achieve adequate accuracy for pedestrian detection (2) it achieves a very low memory usage without reducing detection accuracy on the Caltech Pedestrian dataset.
Cinnamon AI Lab（肉桂人工智能实验室）；Deakin University（迪肯大学）
Convolutional Recurrent Neural Networks (CRNNs) excel at scene text recognition. Unfortunately, they are likely to suffer from vanishing/exploding gradient problems when processing long text images, which are commonly found in scanned documents. This poses a major challenge to goal of completely solving Optical Character Recognition (OCR) problem. Inspired by recently proposed memory-augmented neural networks (MANNs) for long-term sequential modeling, we present a new architecture dubbed Convolutional Multi-way Associative Memory (CMAM) to tackle the limitation of current CRNNs. By leveraging …
Polytechnique Montréal（蒙特利尔理工学院）；The Montréal Institute for Learning Algorithms（蒙特利尔学习算法研究所）；Université de Montréal（蒙特利尔大学）
Very deep convolutional neural networks (CNNs) yield state of the art results on a wide variety of visual recognition problems. A number of state of the the art methods for image recognition are based on networks with well over 100 layers and the performance vs. depth trend is moving towards networks in excess of 1000 layers. In such extremely deep architectures the vanishing or exploding gradient problem becomes a key issue. Recent evidence also indicates that convolutional networks could benefit from an interface to explicitly constructed memory mechanisms interacting with a CNN feature proc…
Radboud University Medical Center（拉德堡德大学医学中心）；Computational Pathology Group（计算病理学小组）
To train deep convolutional neural networks, the input data and the intermediate activations need to be kept in memory to calculate the gradient descent step. Given the limited memory available in the current generation accelerator cards, this limits the maximum dimensions of the input data. We demonstrate a method to train convolutional neural networks holding only parts of the image in memory while giving equivalent results. We quantitatively compare this new way of training convolutional neural networks with conventional training. In addition, as a proof of concept, we train a convolutional…
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
In this paper, we present a novel deep learning based approach for addressing the problem of interaction recognition from a first person perspective. The proposed approach uses a pair of convolutional neural networks, whose parameters are shared, for extracting frame level features from successive frames of the video. The frame level features are then aggregated using a convolutional long short-term memory. The hidden state of the convolutional long short-term memory, after all the input video frames are processed, is used for classification in to the respective categories. The two branches of…
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Developing a technique for the automatic analysis of surveillance videos in order to identify the presence of violence is of broad interest. In this work, we propose a deep neural network for the purpose of recognizing violent videos. A convolutional neural network is used to extract frame level features from a video. The frame level features are then aggregated using a variant of the long short term memory that uses convolutional gates. The convolutional neural network along with the convolutional long short term memory is capable of capturing localized spatio-temporal features which enables …
In this work, we propose ReStoCNet, a residual stochastic multilayer convolutional Spiking Neural Network (SNN) composed of binary kernels, to reduce the synaptic memory footprint and enhance the computational efficiency of SNNs for complex pattern recognition tasks. ReStoCNet consists of an input layer followed by stacked convolutional layers for hierarchical input feature extraction, pooling layers for dimensionality reduction, and fully-connected layer for inference. In addition, we introduce residual connections between the stacked convolutional layers to improve the hierarchical feature l…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Microsoft Research（微软研究院）
In this work, we investigate the use of sparsity-inducing regularizers during training of Convolution Neural Networks (CNNs). These regularizers encourage that fewer connections in the convolution and fully connected layers take non-zero values and in effect result in sparse connectivity between hidden units in the deep network. This in turn reduces the memory and runtime cost involved in deploying the learned CNNs. We show that training with such regularization can still be performed using stochastic gradient descent implying that it can be used easily in existing codebases. Experimental eval…
Text recognition in natural scene is a challenging problem due to the many factors affecting text appearance. In this paper, we presents a method that directly transcribes scene text images to text without needing of sophisticated character segmentation. We leverage recent advances of deep neural networks to model the appearance of scene text images with temporal dynamics. Specifically, we integrates convolutional neural network (CNN) and recurrent neural network (RNN) which is motivated by observing the complementary modeling capabilities of the two models. The main contribution of this work …
Convolutional Neural Networks (CNNs) usually use the same activation function, such as RELU, for all convolutional layers. There are performance limitations of just using RELU. In order to achieve better classification performance, reduce training and testing times, and reduce power consumption and memory usage, a new "Compressed Multi-function CNN" is developed. Google's Inception-V4, for example, is a very deep CNN that consists of 4 Inception-A blocks, 7 Inception-B blocks, and 3 Inception-C blocks. RELU is used for all convolutional layers. A new "Compressed Multi-function Inception-V4" (C…
Isfahan University of Technology（伊斯法罕理工大学）；McMaster University（麦克马斯特大学）
For convolutional neural networks (CNNs) that have a large volume of input data, memory management becomes a major concern. Memory cost reduction can be an effective way to deal with these problems that can be realized through different techniques such as feature map pruning, input data splitting, etc. Among various methods existing in this area of research, splitting the network structure is an interesting research field, and there are a few works done in this area. In this study, the problem of reducing memory utilization using network structure splitting is addressed. A new technique is pro…
Automating the detection of anomalous events within long video sequences is challenging due to the ambiguity of how such events are defined. We approach the problem by learning generative models that can identify anomalies in videos using limited supervision. We propose end-to-end trainable composite Convolutional Long Short-Term Memory (Conv-LSTM) networks that are able to predict the evolution of a video sequence from a small number of input frames. Regularity scores are derived from the reconstruction errors of a set of predictions with abnormal video sequences yielding lower regularity sco…
Deep convolutional neural network (DCNN) has achieved remarkable performance on object detection and speech recognition in recent years. However, the excellent performance of a DCNN incurs high computational complexity and large memory requirement. In this paper, an equal distance nonuniform quantization (ENQ) scheme and a K-means clustering nonuniform quantization (KNQ) scheme are proposed to reduce the required memory storage when low complexity hardware or software implementations are considered. For the VGG-16 and the AlexNet, the proposed nonuniform quantization schemes reduce the number …
Training a deep convolutional neural net typically starts with a random initialisation of all filters in all layers which severely reduces the forward signal and back-propagated error and leads to slow and sub-optimal training. Techniques that counter that focus on either increasing the signal or increasing the gradients adaptively but the model behaves very differently at the beginning of training compared to later when stable pathways through the net have been established. To compound this problem the effective minibatch size varies greatly between layers at different depths and between indi…
For convolutional neural networks, a simple algorithm to reduce off-chip memory accesses is proposed by maximally utilizing on-chip memory in a neural process unit. Especially, the algorithm provides an effective way to process a module which consists of multiple branches and a merge layer. For Inception-V3 on Samsung's NPU in Exynos, our evaluation shows that the proposed algorithm makes off-chip memory accesses reduced by 1/50, and accordingly achieves 97.59 % reduction in the amount of feature-map data to be transferred from/to off-chip memory.
This paper proposes using sketch algorithms to represent the votes in Hough transforms. Replacing the accumulator array with a sketch (Sketch Hough Transform - SHT) significantly reduces the memory needed to compute a Hough transform. We also present a new sketch, Count Median Update, which works better than known sketch methods for replacing the accumulator array in the Hough Transform.
Personality computing and affective computing, where the recognition of personality traits is essential, have gained increasing interest and attention in many research areas recently. We propose a novel approach to recognize the Big Five personality traits of people from videos. Personality and emotion affect the speaking style, facial expressions, body movements, and linguistic factors in social contexts, and they are affected by environmental elements. We develop a multimodal system to recognize apparent personality based on various modalities such as the face, environment, audio, and transc…
We present a deep convolutional decoder architecture that can generate volumetric 3D outputs in a compute- and memory-efficient manner by using an octree representation. The network learns to predict both the structure of the octree, and the occupancy values of individual cells. This makes it a particularly valuable technique for generating 3D shapes. In contrast to standard decoders acting on regular voxel grids, the architecture does not have cubic complexity. This allows representing much higher resolution outputs with a limited memory budget. We demonstrate this in several application doma…
University of Southern California（南加州大学）；US Army Research Laboratory（美国陆军研究实验室）
Recent advances in convolutional neural networks have shown promising results in 3D shape completion. But due to GPU memory limitations, these methods can only produce low-resolution outputs. To inpaint 3D models with semantic plausibility and contextual details, we introduce a hybrid framework that combines a 3D Encoder-Decoder Generative Adversarial Network (3D-ED-GAN) and a Long-term Recurrent Convolutional Network (LRCN). The 3D-ED-GAN is a 3D convolutional neural network trained with a generative adversarial paradigm to fill missing 3D data in low-resolution. LRCN adopts a recurrent neura…
University of Southern California（南加州大学）；Google Inc.（谷歌公司）
Deep convolutional networks are well-known for their high computational and memory demands. Given limited resources, how does one design a network that balances its size, training time, and prediction accuracy? A surprisingly effective approach to trade accuracy for size and speed is to simply reduce the number of channels in each convolutional layer by a fixed fraction and retrain the network. In many cases this leads to significantly smaller networks with only minimal changes to accuracy. In this paper, we take a step further by empirically examining a strategy for deactivating connections b…
Center for Cognitive Skill Enhancement（认知技能提升中心）；Independent University Bangladesh（孟加拉国独立大学）
Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and conducting supervised training tends to increase the complexity. With the introduction of Fully Convolutional Neural Network, which uses finer strides and utilizes deconvolutional layers for upsampling, it has been a go to for any image segmentation task. In this paper, we propose two segmentation architecture which not only needs one-third the parameters t…
Deep convolutional Neural Networks (CNN) are the state-of-the-art performers for object detection task. It is well known that object detection requires more computation and memory than image classification. Thus the consolidation of a CNN-based object detection for an embedded system is more challenging. In this work, we propose LCDet, a fully-convolutional neural network for generic object detection that aims to work in embedded systems. We design and develop an end-to-end TensorFlow(TF)-based model. Additionally, we employ 8-bit quantization on the learned weights. We use face detection as a…
Humans can effectively find salient regions in complex scenes. Self-attention mechanisms were introduced into Computer Vision (CV) to achieve this. Attention Augmented Convolutional Network (AANet) is a mixture of convolution and self-attention, which increases the accuracy of a typical ResNet. However, The complexity of self-attention is O(n2) in terms of computation and memory usage with respect to the number of input tokens. In this project, we propose EAANet: Efficient Attention Augmented Convolutional Networks, which incorporates efficient self-attention mechanisms in a convolution and se…
Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58x faster convolutional operations and 32x memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are…
CSEM SA（瑞士电子与微技术中心）；Swiss Federal Institute of Technology, ETH Zurich（苏黎世联邦理工学院）；University of Bologna（博洛尼亚大学）
While the accuracy of convolutional neural networks has achieved vast improvements by introducing larger and deeper network architectures, also the memory footprint for storing their parameters and activations has increased. This trend especially challenges power- and resource-limited accelerator designs, which are often restricted to store all network data in on-chip memory to avoid interfacing energy-hungry external memories. Maximizing the network size that fits on a given accelerator thus requires to maximize its memory utilization. While the traditionally used ping-pong buffering techniqu…
In this paper we propose a technique which avoids the evaluation of certain convolutional filters in a deep neural network. This allows to trade-off the accuracy of a deep neural network with the computational and memory requirements. This is especially important on a constrained device unable to hold all the weights of the network in memory.
Traditional 3D convolutions are computationally expensive, memory intensive, and due to large number of parameters, they often tend to overfit. On the other hand, 2D CNNs are less computationally expensive and less memory intensive than 3D CNNs and have shown remarkable results in applications like image classification and object recognition. However, in previous works, it has been observed that they are inferior to 3D CNNs when applied on a spatio-temporal input. In this work, we propose a convolutional block which extracts the spatial information by performing a 2D convolution and extracts t…
Fingerprint recognition is often a game-changing step in establishing evidence against criminals. However, we are increasingly finding that criminals deliberately alter their fingerprints in a variety of ways to make it difficult for technicians and automatic sensors to recognize their fingerprints, making it tedious for investigators to establish strong evidence against them in a forensic procedure. In this sense, deep learning comes out as a prime candidate to assist in the recognition of damaged fingerprints. In particular, convolution algorithms. In this paper, we focus on the recognition …
Central University of Finance and Economics（中央财经大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Watrix technology limited co. ltd（Watrix科技有限公司）
As deep neural networks are increasingly used in applications suited for low-power devices, a fundamental dilemma becomes apparent: the trend is to grow models to absorb increasing data that gives rise to memory intensive; however low-power devices are designed with very limited memory that can not store large models. Parameters pruning is critical for deep model deployment on low-power devices. Existing efforts mainly focus on designing highly efficient structures or pruning redundant connections for networks. They are usually sensitive to the tasks or relay on dedicated and expensive hashing…
Normandie University（诺曼底大学）；University of Rouen（鲁昂大学）
Unconstrained handwritten text recognition is a major step in most document analysis tasks. This is generally processed by deep recurrent neural networks and more specifically with the use of Long Short-Term Memory cells. The main drawbacks of these components are the large number of parameters involved and their sequential execution during training and prediction. One alternative solution to using LSTM cells is to compensate the long time memory loss with an heavy use of convolutional layers whose operations can be executed in parallel and which imply fewer parameters. In this paper we presen…
University of Bucharest（布加勒斯特大学）；Romanian Young Academy（罗马尼亚青年科学院）；``Carol Davila'' University of Medicine and Pharmacy（“卡罗尔·达维拉”医药大学）
In this paper, we present our system for the RSNA Intracranial Hemorrhage Detection challenge. The proposed system is based on a lightweight deep neural network architecture composed of a convolutional neural network (CNN) that takes as input individual CT slices, and a Long Short-Term Memory (LSTM) network that takes as input feature embeddings provided by the CNN. For efficient processing, we consider various feature selection methods to produce a subset of useful CNN features for the LSTM. Furthermore, we reduce the CT slices by a factor of 2x, allowing ourselves to train the model faster. …
School of Information Technology, University of Cincinnati（辛辛那提大学信息技术学院）；School of Computing and Informatics, University of Louisiana at Lafayette（路易斯安那大学拉法叶分校计算与信息学院）
Spatiotemporal sequence prediction is an important problem in deep learning. We study next-frame(s) video prediction using a deep-learning-based predictive coding framework that uses convolutional, long short-term memory (convLSTM) modules. We introduce a novel reduced-gate convolutional LSTM(rgcLSTM) architecture that requires a significantly lower parameter budget than a comparable convLSTM. By using a single multi-function gate, our reduced-gate model achieves equal or better next-frame(s) prediction accuracy than the original convolutional LSTM while using a smaller parameter budget, there…
Ben-Gurion University（本-古里安大学）；The Kreitman School of Advanced Graduate Studies（克雷特曼高级研究生学院）
Live cell microscopy sequences exhibit complex spatial structures and complicated temporal behaviour, making their analysis a challenging task. Considering cell segmentation problem, which plays a significant role in the analysis, the spatial properties of the data can be captured using Convolutional Neural Networks (CNNs). Recent approaches show promising segmentation results using convolutional encoder-decoders such as the U-Net. Nevertheless, these methods are limited by their inability to incorporate temporal information, that can facilitate segmentation of individual touching cells or of …
National University of Singapore（新加坡国立大学）；University of Science and Technology of China（中国科学技术大学）
A standard hardware bottleneck when training deep neural networks is GPU memory. The bulk of memory is occupied by caching intermediate tensors for gradient computation in the backward pass. We propose a novel method to reduce this footprint - Dropping Intermediate Tensors (DropIT). DropIT drops min-k elements of the intermediate tensors and approximates gradients from the sparsified tensors in the backward pass. Theoretically, DropIT reduces noise on estimated gradients and therefore has a higher rate of convergence than vanilla-SGD. Experiments show that we can drop up to 90\% of the interme…
OPPO US Research Center（OPPO美国研究中心）；University of Wisconsin, Madison（威斯康星大学麦迪逊分校）；New York University（纽约大学）；Harvard University（哈佛大学）
The memory consumption of most Convolutional Neural Network (CNN) architectures grows rapidly with increasing depth of the network, which is a major constraint for efficient network training on modern GPUs with limited memory, embedded systems, and mobile devices. Several studies show that the feature maps (as generated after the convolutional layers) are the main bottleneck in this memory problem. Often, these feature maps mimic natural photographs in the sense that their energy is concentrated in the spectral domain. Although embedding CNN architectures in the spectral domain is widely explo…
Convolutional Neural Networks(CNN) has had a great success in the recent past, because of the advent of faster GPUs and memory access. CNNs are really powerful as they learn the features from data in layers such that they exhibit the structure of the V-1 features of the human brain. A huge bottleneck, in this case, is that CNNs are very large and have a very high memory footprint, and hence they cannot be employed on devices with limited storage such as mobile phone, IoT etc. In this work, we study the model complexity versus accuracy trade-off on MNSIT dataset, and give a concrete framework f…
Binarization is an attractive strategy for implementing lightweight Deep Convolutional Neural Networks (CNNs). Despite the unquestionable savings offered, memory footprint above all, it may induce an excessive accuracy loss that prevents a widespread use. This work elaborates on this aspect introducing TentacleNet, a new template designed to improve the predictive performance of binarized CNNs via parallelization. Inspired by the ensemble learning theory, it consists of a compact topology that is end-to-end trainable and organized to minimize memory utilization. Experimental results collected …
Yale University（耶鲁大学）；Siemens Medical Solutions USA, Inc.（美国西门子医疗解决方案公司）
Subject motion in whole-body dynamic PET introduces inter-frame mismatch and seriously impacts parametric imaging. Traditional non-rigid registration methods are generally computationally intense and time-consuming. Deep learning approaches are promising in achieving high accuracy with fast speed, but have yet been investigated with consideration for tracer distribution changes or in the whole-body scope. In this work, we developed an unsupervised automatic deep learning-based framework to correct inter-frame body motion. The motion estimation network is a convolutional neural network with a c…
Robotic and Technology of Computers Lab（机器人及计算机技术实验室）；School of Electrical, Computer and Energy Engineering（电气、计算机与能源工程学院）；University of Seville（塞维利亚大学）；Arizona State University（亚利桑那州立大学）
Deep learning has significantly advanced the state of the art in artificial intelligence, gaining wide popularity from both industry and academia. Special interest is around Convolutional Neural Networks (CNN), which take inspiration from the hierarchical structure of the visual cortex, to form deep layers of convolutional operations, along with fully connected classifiers. Hardware implementations of these deep CNN architectures are challenged with memory bottlenecks that require many convolution and fully-connected layers demanding large amount of communication for parallel computation. Mult…
In this work we introduce a convolutional neural network (CNN) that jointly handles low-, mid-, and high-level vision tasks in a unified architecture that is trained end-to-end. Such a universal network can act like a `swiss knife' for vision tasks; we call this architecture an UberNet to indicate its overarching nature. We address two main technical challenges that emerge when broadening up the range of tasks handled by a single CNN: (i) training a deep architecture while relying on diverse training sets and (ii) training many (potentially unlimited) tasks with a limited memory budget. Proper…
SRM Institute of Science and Technology（SRM科学技术研究所）
Diabetic Retinopathy (DR) is a severe complication that may lead to retinal vascular damage and is one of the leading causes of vision impairment and blindness. DR broadly is classified into two stages - non-proliferative (NPDR), where there are almost no symptoms, except a few microaneurysms, and proliferative (PDR) involving a huge number of microaneurysms and hemorrhages, soft and hard exudates, neo-vascularization, macular ischemia or a combination of these, making it easier to detect. More specifically, DR is usually classified into five levels, labeled 0-4, from 0 indicating no DR to 4 w…
Spatio-Spectroscopic Representation Learning using Unsupervised Convolutional Long-Short Term Memory Networks
Department of Physics and Astronomy, University of Minnesota Twin Cities（物理与天文学系，明尼苏达大学双城分校）；Physics Department, Lancaster University（拉斯特纳大学物理系）；European Space Agency (ESA), European Space Astronomy Centre (ESAC)（欧洲航天局（ESA）、欧洲空间天文学中心（ESAC））；Departments of Physics and Astronomy, Haverford College（物理与天文学系，哈弗德学院）；School of Physical Sciences, The Open University（物理科学学院，开放大学）
In recent years, there have been many popular Convolutional Neural Networks (CNNs), such as Google's Inception-V4, that have performed very well for various image classification problems. These commonly used CNN models usually use the same activation function, such as RELU, for all neurons in the convolutional layers; they are "Single-function CNNs." However, SCNNs may not always be optimal. Thus, a "Multi-function CNN" (MCNN), which uses different activation functions for different neurons, has been shown to outperform a SCNN. Also, CNNs typically have very large architectures that use a lot …
Deploying state-of-the-art CNNs requires power-hungry processors and off-chip memory. This precludes the implementation of CNNs in low-power embedded systems. Recent research shows CNNs sustain extreme quantization, binarizing their weights and intermediate feature maps, thereby saving 8-32\x memory and collapsing energy-intensive sum-of-products into XNOR-and-popcount operations. We present XNORBIN, an accelerator for binary CNNs with computation tightly coupled to memory for aggressive data reuse. Implemented in UMC 65nm technology XNORBIN achieves an energy efficiency of 95 TOp/s/W and an a…
Wireless distributed systems as used in sensor networks, Internet-of-Things and cyber-physical systems, impose high requirements on resource efficiency. Advanced preprocessing and classification of data at the network edge can help to decrease the communication demand and to reduce the amount of data to be processed centrally. In the area of distributed acoustic sensing, the combination of algorithms with a high classification rate and resource-constraint embedded systems is essential. Unfortunately, algorithms for acoustic event detection have a high memory and computational demand and are no…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；Laboratory for Physical Sciences（物理科学实验室）；Booz Allen Hamilton（博思艾伦汉密尔顿）
Due to the computational cost of running inference for a neural network, the need to deploy the inferential steps on a third party's compute environment or hardware is common. If the third party is not fully trusted, it is desirable to obfuscate the nature of the inputs and outputs, so that the third party can not easily determine what specific task is being performed. Provably secure protocols for leveraging an untrusted party exist but are too computational demanding to run in practice. We instead explore a different strategy of fast, heuristic security that we call Connectionist Symbolic Ps…
Singapore University of Technology and Design（新加坡科技设计大学）
Convolutional Neural Networks (CNNs) have been proven to be extremely successful at solving computer vision tasks. State-of-the-art methods favor such deep network architectures for its accuracy performance, with the cost of having massive number of parameters and high weights redundancy. Previous works have studied how to prune such CNNs weights. In this paper, we go to another extreme and analyze the performance of a network stacked with a single convolution kernel across layers, as well as other weights sharing techniques. We name it Deep Anchored Convolutional Neural Network (DACNN). Shari…
Deep Convolutional Neural Networks (CNN) have been successfully applied to many real-life problems. However, the huge memory cost of deep CNN models poses a great challenge of deploying them on memory-constrained devices (e.g., mobile phones). One popular way to reduce the memory cost of deep CNN model is to train binary CNN where the weights in convolution filters are either 1 or -1 and therefore each weight can be efficiently stored using a single bit. However, the compression ratio of existing binary CNN models is upper bounded by around 32. To address this limitation, we propose a novel me…
Université de Montréal（蒙特利尔大学）；MILA；IMT Atlantique（IMT大西洋高等矿业学院）；Lab-STICC（STICC实验室）；ISCAS 2019（ISCAS 2019（会议名称，不提取））
Convolutional Neural Networks (CNNs) are state-of-the-art in numerous computer vision tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and strongly limits their usability in budget-constrained devices such as embedded devices. In this paper, we propose a combination of a new pruning technique and a quantization scheme that effectively reduce the complexity and memory usage of convolutional layers of CNNs, and replace the complex convolutional operation by a low-cost multiplexer. We perform experimen…
Convolutional sparse representations are a form of sparse representation with a structured, translation invariant dictionary. Most convolutional dictionary learning algorithms to date operate in batch mode, requiring simultaneous access to all training images during the learning process, which results in very high memory usage and severely limits the training data that can be used. Very recently, however, a number of authors have considered the design of online convolutional dictionary learning algorithms that offer far better scaling of memory and computational cost with training set size tha…
