相关论文
1997 - International Journal of Remote Sensing
Strategies and best practice for neural network image classification

This paper examines a number of experimental investigations of neural networks used for the classification of remotely sensed satellite imagery at the Joint Research Centre over a period of five years, and attempts to draw some conclusions about 'best practice' techniques to optimize network training and overall classification performance. The paper examines best practice in such areas as: network architecture selection; use of optimization algorithms; scaling of input data; avoidance of chaos effects; use of enhanced feature sets; and use of hybrid classifier methods. It concludes that a vast body of accumulated experience is now available, and that neural networks can be used reliably and with much confidence for routine operational requirements in remote sensing.

2016 - 2017 IEEE Winter Conference on Applications of Computer Vision (WACV)
Subcategory-Aware Convolutional Neural Networks for Object Proposals and Detection

In Convolutional Neural Network (CNN)-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods mainly focus on 2D object detection and cannot estimate detailed properties of objects. In this paper, we propose subcategory-aware CNNs for object detection. We introduce a novel region proposal network that uses subcategory information to guide the proposal generating process, and a new detection network for joint detection and subcategory classification. By using subcategories related to object pose, we achieve state of-the-art performance on both detection and pose estimation on commonly used benchmarks.

2018 - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Deep Parametric Continuous Convolutional Neural Networks

Standard convolutional neural networks assume a grid structured input is available and exploit discrete convolutions as their fundamental building blocks. This limits their applicability to many real-world applications. In this paper we propose Parametric Continuous Convolution, a new learnable operator that operates over non-grid structured data. The key idea is to exploit parameterized kernel functions that span the full continuous vector space. This generalization allows us to learn over arbitrary data structures as long as their support relationship is computable. Our experiments show significant improvement over the state-of-the-art in point cloud segmentation of indoor and outdoor scenes, and lidar motion estimation of driving scenes.

2016 - 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification

Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data variations. In this work, we present a pipeline for learning deep feature representations from multiple domains with Convolutional Neural Networks (CNNs). When training a CNN with data from all the domains, some neurons learn representations shared across several domains, while some others are effective only for a specific one. Based on this important observation, we propose a Domain Guided Dropout algorithm to improve the feature learning procedure. Experiments show the effectiveness of our pipeline and the proposed algorithm. Our methods on the person re-identification problem outperform stateof-the-art methods on multiple datasets by large margins.

2017 - 2017 IEEE International Conference on Computer Vision (ICCV)
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks

Convolutional Neural Networks (CNN) have been regarded as a powerful class of models for image recognition problems. Nevertheless, it is not trivial when utilizing a CNN for learning spatio-temporal video representation. A few studies have shown that performing 3D convolutions is a rewarding approach to capture both spatial and temporal dimensions in videos. However, the development of a very deep 3D CNN from scratch results in expensive computational cost and memory demand. A valid question is why not recycle off-the-shelf 2D networks for a 3D CNN. In this paper, we devise multiple variants of bottleneck building blocks in a residual learning framework by simulating 3 x 3 x 3 convolutions with 1 × 3 × 3 convolutional filters on spatial domain (equivalent to 2D CNN) plus 3 × 1 × 1 convolutions to construct temporal connections on adjacent feature maps in time. Furthermore, we propose a new architecture, named Pseudo-3D Residual Net (P3D ResNet), that exploits all the variants of blocks but composes each in different placement of ResNet, following the philosophy that enhancing structural diversity with going deep could improve the power of neural networks. Our P3D ResNet achieves clear improvements on Sports-1M video classification dataset against 3D CNN and frame-based 2D CNN by 5.3% and 1.8%, respectively. We further examine the generalization performance of video representation produced by our pre-trained P3D ResNet on five different benchmarks and three different tasks, demonstrating superior performances over several state-of-the-art techniques.

2017 - 2017 IEEE International Conference on Computer Vision (ICCV)
MemNet: A Persistent Memory Network for Image Restoration

Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the longterm dependency problem is rarely realized for these very deep models, which results in the prior states/layers having little influence on the subsequent ones. Motivated by the fact that human thoughts have persistency, we propose a very deep persistent memory network (MemNet) that introduces a memory block, consisting of a recursive unit and a gate unit, to explicitly mine persistent memory through an adaptive learning process. The recursive unit learns multi-level representations of the current state under different receptive fields. The representations and the outputs from the previous memory blocks are concatenated and sent to the gate unit, which adaptively controls how much of the previous states should be reserved, and decides how much of the current state should be stored. We apply MemNet to three image restoration tasks, i.e., image denosing, super-resolution and JPEG deblocking. Comprehensive experiments demonstrate the necessity of the MemNet and its unanimous superiority on all three tasks over the state of the arts. Code is available at https://github.com/tyshiwo/MemNet.

2015
Accelerating Deep Convolutional Neural Networks Using Specialized Hardware

Recent breakthroughs in the development of multi-layer convolutional neural networks have led to stateof-the-art improvements in the accuracy of non-trivial recognition tasks such as large-category image classification and automatic speech recognition [1]. These many-layered neural networks are large, complex, and require substantial computing resources to train and evaluate [2]. Unfortunately, these demands come at an inopportune moment due to the recent slowing of gains in commodity processor performance. Hardware specialization in the form of GPGPUs, FPGAs, and ASICs offers a promising path towards major leaps in processing capability while achieving high energy efficiency. To harness specialization, an effort is underway at Microsoft to accelerate Deep Convolutional Neural Networks (CNN) using servers augmented with FPGAs—similar to the hardware that is being integrated into some of Microsoft’s datacenters [3]. Initial efforts to implement a single-node CNN accelerator on a mid-range FPGA show significant promise, resulting in respectable performance relative to prior FPGA designs and high-end GPGPUs, at a fraction of the power. In the future, combining multiple FPGAs over a low-latency communication fabric offers further opportunity to train and evaluate models of unprecedented size and quality. Background State-of-the-art deep convolutional neural networks are typically organized into alternating convolutional and max-pooling neural network layers followed by a number of dense, fully-connected layers—as illustrated in the well-known topology by Krizhevsky et al. in Figure 1 [1]. Each 3D volume represents an input to a layer, and is transformed into a new 3D volume feeding the subsequent layer. In the example below, there are five convolutional layers, three max-pooling layers, and three fully-connected layers. Figure 1. Example of Deep Convolutional Neural Network for Image Classification. Image source: [1]. 1 General Purpose Computing on Graphics Processing Units, Field Programmable Gate Arrays, ApplicationSpecific Integrated Circuits.

2017 - 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching

Leveraging on the recent developments in convolutional neural networks (CNNs), matching dense correspondence from a stereo pair has been cast as a learning problem, with performance exceeding traditional approaches. However, it remains challenging to generate high-quality disparities for the inherently ill-posed regions. To tackle this problem, we propose a novel cascade CNN architecture composing of two stages. The first stage advances the recently proposed DispNet by equipping it with extra up-convolution modules, leading to disparity images with more details. The second stage explicitly rectifies the disparity initialized by the first stage; it couples with the first-stage and generates residual signals across multiple scales. The summation of the outputs from the two stages gives the final disparity. As opposed to directly learning the disparity at the second stage, we show that residual learning provides more effective refinement. Moreover, it also benefits the training of the overall cascade network. Experimentation shows that our cascade residual learning scheme provides state-of-the-art performance for matching stereo correspondence. By the time of the submission of this paper, our method ranks first in the KITTI 2015 stereo benchmark, surpassing the prior works by a noteworthy margin.

2015 - INTERSPEECH
Convolutional neural networks for small-footprint keyword spotting

We explore using Convolutional Neural Networks (CNNs) for a small-footprint keyword spotting (KWS) task. CNNs are attractive for KWS since they have been shown to outperform DNNs with far fewer parameters. We consider two different applications in our work, one where we limit the number of multiplications of the KWS system, and another where we limit the number of parameters. We present new CNN architectures to address the constraints of each applications. We find that the CNN architectures offer between a 27-44% relative improvement in false reject rate compared to a DNN, while fitting into the constraints of each application.

2013 - NIPS
Discriminative Transfer Learning with Tree-based Priors

High capacity classifiers, such as deep neural networks, often struggle on classes that have very few training examples. We propose a method for improving classification performance for such classes by discovering similar classes and transferring knowledge among them. Our method learns to organize the classes into a tree hierarchy. This tree structure imposes a prior over the classifier's parameters. We show that the performance of deep neural networks can be improved by applying these priors to the weights in the last layer. Our method combines the strength of discriminatively trained deep neural networks, which typically require large amounts of training data, with tree-based priors, making deep neural networks work well on infrequent classes as well. We also propose an algorithm for learning the underlying tree structure. Starting from an initial pre-specified tree, this algorithm modifies the tree to make it more pertinent to the task being solved, for example, removing semantic relationships in favour of visual ones for an image classification task. Our method achieves state-of-the-art classification results on the CIFAR-100 image data set and the MIR Flickr image-text data set.

2012 - Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012)
Convolutional neural networks applied to house numbers digit classification

We classify digits of real-world house numbers using convolutional neural networks (ConvNets). Con-vNets are hierarchical feature learning neural networks whose structure is biologically inspired. Unlike many popular vision approaches that are hand-designed, ConvNets can automatically learn a unique set of features optimized for a given task. We augmented the traditional ConvNet architecture by learning multi-stage features and by using Lp pooling and establish a new state-of-the-art of 95.10% accuracy on the SVHN dataset (48% error improvement). Furthermore, we analyze the benefits of different pooling methods and multi-stage features in ConvNets. The source code and a tutorial are available at eblearn.sf.net.

2017 - Remote. Sens.
Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network

Recent research has shown that using spectral–spatial information can considerably improve the performance of hyperspectral image (HSI) classification. HSI data is typically presented in the format of 3D cubes. Thus, 3D spatial filtering naturally offers a simple and effective method for simultaneously extracting the spectral–spatial features within such images. In this paper, a 3D convolutional neural network (3D-CNN) framework is proposed for accurate HSI classification. The proposed method views the HSI cube data altogether without relying on any preprocessing or post-processing, extracting the deep spectral–spatial-combined features effectively. In addition, it requires fewer parameters than other deep learning-based methods. Thus, the model is lighter, less likely to over-fit, and easier to train. For comparison and validation, we test the proposed method along with three other deep learning-based HSI classification methods—namely, stacked autoencoder (SAE), deep brief network (DBN), and 2D-CNN-based methods—on three real-world HSI datasets captured by different sensors. Experimental results demonstrate that our 3D-CNN-based method outperforms these state-of-the-art methods and sets a new record.

2018 - ArXiv
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring

Deep Neural Networks have recently gained lots of success after enabling several breakthroughs in notoriously challenging problems. Training these networks is computationally expensive and requires vast amounts of training data. Selling such pre-trained models can, therefore, be a lucrative business model. Unfortunately, once the models are sold they can be easily copied and redistributed. To avoid this, a tracking mechanism to identify models as the intellectual property of a particular vendor is necessary. In this work, we present an approach for watermarking Deep Neural Networks in a black-box way. Our scheme works for general classification tasks and can easily be combined with current learning algorithms. We show experimentally that such a watermark has no noticeable impact on the primary task that the model is designed for. Moreover, we evaluate the robustness of our proposal against a multitude of practical attacks.

2011 - INTERSPEECH
Improved Bottleneck Features Using Pretrained Deep Neural Networks

Bottleneck features have been shown to be effective in improving the accuracy of automatic speech recognition (ASR) systems. Conventionally, bottleneck features are extracted from a multi-layer perceptron (MLP) trained to predict context-independent monophone states. The MLP typically has three hidden layers and is trained using the backpropagation algorithm. In this paper, we propose two improvements to the training of bottleneck features motivated by recent advances in the use of deep neural networks (DNNs) for speech recognition. First, we show how the use of unsupervised pretraining of a DNN enhances the network’s discriminative power and improves the bottleneck features it generates. Second, we show that a neural network trained to predict context-dependent senone targets produces better bottleneck features than one trained to predict monophone states. Bottleneck features trained using the proposed methods produced a 16% relative reduction in sentence error rate over conventional bottleneck features on a large vocabulary business search task.

2016 - ArXiv
Understanding Deep Neural Networks with Rectified Linear Units

In this paper we investigate the family of functions representable by deep neural networks (DNN) with rectified linear units (ReLU). We give an algorithm to train a ReLU DNN with one hidden layer to *global optimality* with runtime polynomial in the data size albeit exponential in the input dimension. Further, we improve on the known lower bounds on size (from exponential to super exponential) for approximating a ReLU deep net function by a shallower ReLU net. Our gap theorems hold for smoothly parametrized families of "hard" functions, contrary to countable, discrete families known in the literature. An example consequence of our gap theorems is the following: for every natural number $k$ there exists a function representable by a ReLU DNN with $k^2$ hidden layers and total size $k^3$, such that any ReLU DNN with at most $k$ hidden layers will require at least $\frac{1}{2}k^{k+1}-1$ total nodes. Finally, for the family of $\mathbb{R}^n\to \mathbb{R}$ DNNs with ReLU activations, we show a new lowerbound on the number of affine pieces, which is larger than previous constructions in certain regimes of the network architecture and most distinctively our lowerbound is demonstrated by an explicit construction of a *smoothly parameterized* family of functions attaining this scaling. Our construction utilizes the theory of zonotopes from polyhedral theory.

2017 - IEEE Transactions on Pattern Analysis and Machine Intelligence
Squeeze-and-Excitation Networks

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of <inline-formula><tex-math notation="LaTeX">${\sim }$</tex-math><alternatives><mml:math><mml:mo>∼</mml:mo></mml:math><inline-graphic xlink:href="shen-ieq1-2913372.gif"/></alternatives></inline-formula>25 percent. Models and code are available at <uri>https://github.com/hujie-frank/SENet</uri>.

2016 - ECCV
Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks

As 3D movie viewing becomes mainstream and the Virtual Reality (VR) market emerges, the demand for 3D contents is growing rapidly. Producing 3D videos, however, remains challenging. In this paper we propose to use deep neural networks to automatically convert 2D videos and images to a stereoscopic 3D format. In contrast to previous automatic 2D-to-3D conversion algorithms, which have separate stages and need ground truth depth map as supervision, our approach is trained end-to-end directly on stereo pairs extracted from existing 3D movies. This novel training scheme makes it possible to exploit orders of magnitude more data and significantly increases performance. Indeed, Deep3D outperforms baselines in both quantitative and human subject evaluations.

2017 - ArXiv
An Overview of Multi-Task Learning in Deep Neural Networks

Multi-task learning (MTL) has led to successes in many applications of machine learning, from natural language processing and speech recognition to computer vision and drug discovery. This article aims to give a general overview of MTL, particularly in deep neural networks. It introduces the two most common methods for MTL in Deep Learning, gives an overview of the literature, and discusses recent advances. In particular, it seeks to help ML practitioners apply MTL by shedding light on how MTL works and providing guidelines for choosing appropriate auxiliary tasks.

2017 - ArXiv
CryptoDL: Deep Neural Networks over Encrypted Data

Machine learning algorithms based on deep neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which is often privacy sensitive. To address this issue, we develop new techniques to provide solutions for running deep neural networks over encrypted data. In this paper, we develop new techniques to adopt deep neural networks within the practical limitation of current homomorphic encryption schemes. More specifically, we focus on classification of the well-known convolutional neural networks (CNN). First, we design methods for approximation of the activation functions commonly used in CNNs (i.e. ReLU, Sigmoid, and Tanh) with low degree polynomials which is essential for efficient homomorphic encryption schemes. Then, we train convolutional neural networks with the approximation polynomials instead of original activation functions and analyze the performance of the models. Finally, we implement convolutional neural networks over encrypted data and measure performance of the models. Our experimental results validate the soundness of our approach with several convolutional neural networks with varying number of layers and structures. When applied to the MNIST optical character recognition tasks, our approach achieves 99.52\% accuracy which significantly outperforms the state-of-the-art solutions and is very close to the accuracy of the best non-private version, 99.77\%. Also, it can make close to 164000 predictions per hour. We also applied our approach to CIFAR-10, which is much more complex compared to MNIST, and were able to achieve 91.5\% accuracy with approximation polynomials used as activation functions. These results show that CryptoDL provides efficient, accurate and scalable privacy-preserving predictions.

2016 - ECCV
Single Image Dehazing via Multi-scale Convolutional Neural Networks

The performance of existing image dehazing methods is limited by hand-designed features, such as the dark channel, color disparity and maximum contrast, with complex fusion schemes. In this paper, we propose a multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps. The proposed algorithm consists of a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale net which refines results locally. To train the multi-scale deep network, we synthesize a dataset comprised of hazy images and corresponding transmission maps based on the NYU Depth dataset. Extensive experiments demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods on both synthetic and real-world images in terms of quality and speed.

Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification

Darko Stefanovic
|
Dubravko Culibrk
|
Srdjan Sladojevic
|
Marko Arsenovic
|
Andras Anderla
|
D. Culibrk
|
Darko Stefanović
|
S. Sladojevic
|
M. Arsenovic
|
A. Anderla
|
D. Ćulibrk

Abstract:The latest generation of convolutional neural networks (CNNs) has achieved impressive results in the field of image classification. This paper is concerned with a new approach to the development of plant disease recognition model, based on leaf image classification, by the use of deep convolutional networks. Novel way of training and the methodology used facilitate a quick and easy system implementation in practice. The developed model is able to recognize 13 different types of plant diseases out of healthy leaves, with the ability to distinguish plant leaves from their surroundings. According to our knowledge, this method for plant disease recognition has been proposed for the first time. All essential steps required for implementing this disease recognition model are fully described throughout the paper, starting from gathering images in order to create a database, assessed by agricultural experts. Caffe, a deep learning framework developed by Berkley Vision and Learning Centre, was used to perform the deep CNN training. The experimental results on the developed model achieved precision between 91% and 98%, for separate class tests, on average 96.3%.

摘要：最新一代的卷积神经网络在图像分类领域取得了令人印象深刻的成果。本文提出了一种利用深度卷积网络建立基于叶片图像分类的植物病害识别模型的新方法。新颖的培训方式和使用的方法有助于在实践中快速、轻松地实施系统。开发的模型能够从健康的叶片中识别出13种不同类型的植物疾病，并能够区分植物叶片及其周围环境。据我们所知，这种植物病害识别方法是首次提出的。本白皮书全面介绍了实施这一疾病识别模型所需的所有基本步骤，从收集图像开始，以创建一个由农业专家评估的数据库。使用伯克利视觉与学习中心开发的深度学习框架Caffe进行CNN深度训练。在所开发的模型上的实验结果达到了91%到98%的准确率，对于分类测试，平均为96.3%。

参考文献

[1]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[2]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  S. Chakraborty,et al.  Climate change: potential impact on plant diseases. , 2000, Environmental pollution.

[4]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[5]  Kazi Md. Rokibul Alam,et al.  Tea Leaf Diseases Recognition using Neural Network Ensemble , 2015 .

[6]  Juan C. Caicedo,et al.  Fine-tuning Deep Convolutional Networks for Plant Recognition , 2015, CLEF.

[7]  Jayme Garcia Arnal Barbedo,et al.  Digital image processing techniques for detecting, quantifying and classifying plant diseases , 2013, SpringerPlus.

[8]  Klaus-Robert Müller,et al.  Kernel Analysis of Deep Networks , 2011, J. Mach. Learn. Res..

[9]  T. Zwet.  PRESENT WORLDWIDE DISTRIBUTION OF FIRE BLIGHT , 1996 .

[10]  F. Beed,et al.  Plant disease diagnostic capabilities and networks. , 2009, Annual review of phytopathology.

[11]  Clément Farabet,et al.  Torch7: A Matlab-like Environment for Machine Learning , 2011, NIPS 2011.

[12]  Honglak Lee,et al.  Deep learning for detecting robotic grasps , 2013, Int. J. Robotics Res..

[13]  Reza Ehsani,et al.  Review: A review of advanced techniques for detecting plant diseases , 2010 .

[14]  Joseph Howse.  OpenCV computer vision with Python : learn to capture videos, manipulate images, and track objects with Python using the OpenCV Library , 2013 .

[15]  Tara N. Sainath,et al.  Improving deep neural networks for LVCSR using rectified linear units and dropout , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[16]  Kaur Prabhjot,et al.  DOFCM: A Robust Clustering Technique Based upon Density , 2011 .

[17]  K. Garrett,et al.  Climate change effects on plant disease: genomes to ecosystems. , 2006, Annual review of phytopathology.

[18]  J. M. Hans du Buf,et al.  A review of recent texture segmentation and feature extraction techniques , 1993 .

[19]  S. Chakraborty,et al.  Climate change and plant disease management. , 1999, Annual review of phytopathology.

[20]  M. Hemalatha,et al.  Identification of Cotton Diseases Based on Cross Information Gain_Deep Forward Neural Network Classifier with PSO Feature Selection , 2013 .

[21]  L. Plümer,et al.  Original paper: Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance , 2010 .

[22]  A. Roli.  Artificial Neural Networks , 2012, Lecture Notes in Computer Science.

[23]  Gui-Song Xia,et al.  Deep Learning for Remote Sensing Image Understanding , 2016, J. Sensors.

[24]  D. J. Rogers,et al.  Global Transport Networks and Infectious Disease Spread , 2006, Advances in Parasitology.

[25]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[26]  Mohak Shah,et al.  Comparative Study of Caffe, Neon, Theano, and Torch for Deep Learning , 2015, ArXiv.

[27]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[28]  Alice N. Cheeran,et al.  Color Transform Based Approach for Disease Spot Detection on Plant Leaf , 2012 .

[29]  Miguel Ángel Guevara-López,et al.  Convolutional neural networks for mammography mass lesion classification , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[30]  Peter J. Hudson,et al.  Evaluating the links between climate, disease spread, and amphibian declines , 2008, Proceedings of the National Academy of Sciences.

[31]  Roland T. V. Fox,et al.  Plant disease diagnosis , 2006 .

[32]  Adriana Romero Soriano.  Assisting the training of deep neural networks with applications to computer vision , 2015 .

[33]  Ji-min Zhao,et al.  Study on Plant Disease Detection Based on Near Field Acoustic Holography , 2018 .

[34]  B. Frey,et al.  Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning , 2015, Nature Biotechnology.

[35]  Razvan Pascanu,et al.  Theano: Deep Learning on GPUs with Python , 2012 .

[36]  Prajwala R Reddy,et al.  PLANT DISEASE DETECTION TECHNIQUETOOL- A THEORETICAL APPROACH , 2015 .

[37]  Luca Maria Gambardella,et al.  Flexible, High Performance Convolutional Neural Networks for Image Classification , 2011, IJCAI.

[38]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[39]  Anne-Katrin Mahlein,et al.  Recent advances in sensing plant diseases for precision crop protection , 2012, European Journal of Plant Pathology.

[40]  Malik Braik,et al.  Fast and Accurate Detection and Classification of Plant Diseases , 2011 .

[41]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[42]  Zhou Zhi,et al.  Neural Network Ensemble , 2002 .

[43]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[44]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[45]  Zhang Wan-guo,et al.  Particle Swarm Optimization(PSO) Algorithm , 2003 .

[46]  Douglas M. Hawkins,et al.  The Problem of Overfitting , 2004, J. Chem. Inf. Model..

[47]  Sanjay B. Patil,et al.  LEAF DISEASE SEVERITY MEASUREMENT USING IMAGE PROCESSING , 2011 .

[48]  L. Plümer,et al.  Development of spectral indices for detecting and identifying plant diseases , 2013 .

[49]  Stephen Gould,et al.  Decomposing a scene into geometric and semantically consistent regions , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[50]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

引用
Spectral and textural analysis of high resolution data for the automatic detection of grape vine diseases. (Analyses spectrale et texturale de données haute résolution pour la détection automatique des maladies de la vigne)
2019
A novel approach based on deep learning techniques and UAVs to yield assessment of paddy fields
2017 9th International Conference on Knowledge and Systems Engineering (KSE)
2017
Elma Bitkisindeki Hastalıkların Yapay Zekâ Yöntemleri ile Tespiti ve Yapay Zekâ Yöntemlerinin Performanslarının Karşılaştırılması
2020
Deep Reinforcement Learning for Greenhouse Climate Control
2020 IEEE International Conference on Knowledge Graph (ICKG)
2020
An Efficient Deep Learning Model for Olive Diseases Detection
International Journal of Advanced Computer Science and Applications
2019
Automatic Recognition of Tea Diseases Based on Deep Learning
Advances in Forest Management under Global Change
2020
Various Frameworks and Libraries of Machine Learning and Deep Learning: A Survey
Archives of Computational Methods in Engineering
2019
Examination of Image Features Considering Short-Term Changes in Plant Water Stress
2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)
2020
Local Motion Planner for Autonomous Navigation in Vineyards with a RGB-D Camera-Based Algorithm and Deep Learning Synergy
Machines
2020
Towards a Decentralized, Autonomous Multiagent Framework for Mitigating Crop Loss
ArXiv
2019
Big Scientific Data Management: First International Conference, BigSDM 2018, Beijing, China, November 30 – December 1, 2018, Revised Selected Papers
BigSDM
2019
Potato Virus Y Detection in Seed Potatoes Using Deep Learning on Hyperspectral Images
Front. Plant Sci.
2019
iCassava 2019Fine-Grained Visual Categorization Challenge
ArXiv
2019
Unusual Event Detection in Surveillance Video Using Transfer Learning
2019 International Conference on Information Technology (ICIT)
2019
Convolutional Neural Networks accurately predict cover fractions of plant species and communities in Unmanned Aerial Vehicle imagery
Remote Sensing in Ecology and Conservation
2020
Improving Image-Based Plant Disease Classification With Generative Adversarial Network Under Limited Training Set
Frontiers in Plant Science
2020
Classification of tongue color based on CNN
2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)(
2017
Computerized tongue coating nature diagnosis using convolutional neural network
2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)(
2017
Tomato Diseases and Pests Detection Based on Improved Yolo V3 Convolutional Neural Network
Frontiers in Plant Science
2020
Identification of maize disease based on transfer learning
Journal of Physics: Conference Series
2020