How can we discover and succinctly summarize the concepts that a neural network has learned? Such a task is of great importance in applications of networks in areas of inference that involve classification, like medical diagnosis based on fMRI/x-ray etc. In this work, we propose a framework to categorize the concepts a network learns based on the way it clusters a set of input examples, clusters neurons based on the examples they activate for, and input features all in the same latent space. This framework is unsupervised and can work without any labels for input features, it only needs access to internal activations of the network for each input example, thereby making it widely applicable. We extensively evaluate the proposed method and demonstrate that it produces human-understandable and coherent concepts that a ResNet-18 has learned on the CIFAR-100 dataset.
Combient Mix AB；Combient Competence Centre for Data Engineering Sciences（Combient数据工程科学能力中心）；Uppsala University（乌普萨拉大学）
We investigate the ability to detect slag formations in images from inside a Grate-Kiln system furnace with two deep convolutional neural networks. The conditions inside the furnace cause occasional obstructions of the camera view. Our approach suggests dealing with this problem by introducing a convLSTM-layer in the deep convolutional neural network. The results show that it is possible to achieve sufficient performance to automate the decision of timely countermeasures in the industrial operational setting. Furthermore, the addition of the convLSTM-layer results in fewer outlying predictions…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
Convolutional neural networks have been successfully applied to various NLP tasks. However, it is not obvious whether they model different linguistic patterns such as negation, intensification, and clause compositionality to help the decision-making process. In this paper, we apply visualization techniques to observe how the model can capture different linguistic features and how these features can affect the performance of the model. Later on, we try to identify the model errors and their sources. We believe that interpreting CNNs is the first step to understand the underlying semantic featur…
Yonsei University College of Medicine（延世大学医学院）；Severance Hospital（世福兰斯医院）；Yonsei University（延世大学）
The conventional CNN, widely used for two-dimensional images, however, is not directly applicable to non-regular geometric surface, such as a cortical thickness. We propose Geometric CNN (gCNN) that deals with data representation over a spherical surface and renders pattern recognition in a multi-shell mesh structure. The classification accuracy for sex was significantly higher than that of SVM and image based CNN. It only uses MRI thickness data to classify gender but this method can expand to classify disease from other MRI or fMRI data
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；University of Mannheim（曼海姆大学）
Convolutional neural networks (CNNs) have achieved astonishing performance on various image classification tasks, but it is difficult for humans to understand how a classification comes about. Recent literature proposes methods to explain the classification process to humans. These focus mostly on visualizing feature maps and filter weights, which are not very intuitive for non-experts in analyzing a CNN classification. In this paper, we propose FilTag, an approach to effectively explain CNNs even to non-experts. The idea is that when images of a class frequently activate a convolutional filte…
With the success of deep learning, recent efforts have been focused on analyzing how learned networks make their classifications. We are interested in analyzing the network output based on the network structure and information flow through the network layers. We contribute an algorithm for 1) analyzing a deep network to find neurons that are 'important' in terms of the network classification outcome, and 2)automatically labeling the patches of the input image that activate these important neurons. We propose several measures of importance for neurons and demonstrate that our technique can be u…
East China University of Science and Technology（华东理工大学）
With the improvement of computer performance and the increase of data volume, the object detection based on convolutional neural network (CNN) has become the main algorithm for object detection. This paper summarizes the research progress of convolutional neural networks and their applications in object detection, and focuses on analyzing and discussing a specific idea and method of applying convolutional neural networks for object detection, pointing out the current deficiencies and future development direction.
Despite significant efforts over the last few years to build a robust automatic speech recognition (ASR) system for different acoustic settings, the performance of the current state-of-the-art technologies significantly degrades in noisy reverberant environments. Convolutional Neural Networks (CNNs) have been successfully used to achieve substantial improvements in many speech processing applications including distant speech recognition (DSR). However, standard CNN architectures were not efficient in capturing long-term speech dynamics, which are essential in the design of a robust DSR system.…
Mobility-GCN: a human mobility-based graph convolutional network for tracking and analyzing the spatial dynamics of the synthetic opioid crisis in the USA, 2013-2020
Since frequent severe droughts are lengthening the dry season in the Amazon Rainforest, it is important to detect wildfires promptly and forecast possible spread for effective suppression response. Current wildfire detection models are not versatile enough for the low-technology conditions of South American hot spots. This deep learning study first trains a Fully Convolutional Neural Network on Landsat 8 images of Ecuador and the Galapagos, using Green and Short-wave Infrared bands to predict pixel-level binary fire masks. This model achieves a 0.962 validation F2 score and a 0.932 F2 score on…
Top-down information plays a central role in human perception, but plays relatively little role in many current state-of-the-art deep networks, such as Convolutional Neural Networks (CNNs). This work seeks to explore a path by which top-down information can have a direct impact within current deep networks. We explore this path by learning and using "generators" corresponding to the network internal effects of three types of transformation (each a restriction of a general affine transformation): rotation, scaling, and translation. We demonstrate how these learned generators can be used to tran…
Current saliency methods require to learn large scale regional features using small convolutional kernels, which is not possible with a simple feed-forward network. Some methods solve this problem by using segmentation into superpixels while others downscale the image through the network and rescale it back to its original size. The objective of this paper is to show that saliency convolutional neural networks (CNN) can be improved by using a Green's function convolution (GFC) to extrapolate edges features into salient regions. The GFC acts as a gradient integrator, allowing to produce salienc…
Ensemble learning is a method of combining multiple trained models to improve model accuracy. We propose the usage of such methods, specifically ensemble average, inside Convolutional Neural Network (CNN) architectures by replacing the single convolutional layers with Inner Average Ensembles (IEA) of multiple convolutional layers. Empirical results on different benchmarking datasets show that CNN models using IEA outperform those with regular convolutional layers. A visual and a similarity score analysis of the features generated from IEA explains why it boosts the model performance.
Northeast Yucai Foreign Language School（东北育才外国语学校）；Northwestern University（西北大学）；Shenyang Pharmaceutical University（沈阳药科大学）
Because of their abundance of amino acids, polysaccharides, and many other nutrients that benefit human beings, mushrooms are deservedly popular as dietary cuisine both worldwide and in China. However, if people eat poisonous fungi by mistake, they may suffer from nausea, vomiting, mental disorder, acute anemia, or even death. Each year in China, there are around 8000 people became sick, and 70 died as a result of eating toxic mushrooms by mistake. It is counted that there are thousands of kinds of mushrooms among which only around 900 types are edible, thus without specialized knowledge, the …
National Taiwan University（台湾大学）；Soochow University（东吴大学）
Candlesticks are graphical representations of price movements for a given period. The traders can discovery the trend of the asset by looking at the candlestick patterns. Although deep convolutional neural networks have achieved great success for recognizing the candlestick patterns, their reasoning hides inside a black box. The traders cannot make sure what the model has learned. In this contribution, we provide a framework which is to explain the reasoning of the learned model determining the specific candlestick patterns of time series. Based on the local search adversarial attacks, we show…
Indraprastha Institute of Information Technology Delhi（德里英德拉普拉斯塔信息技术学院）；Inria Saclay（法国国家信息与自动化研究所萨克雷中心）；CNRS（法国国家科学研究中心）；ESIEE Paris（巴黎高等电子工程师学院）
This work addresses the problem of analyzing multi-channel time series data %. In this paper, we by proposing an unsupervised fusion framework based on %the recently proposed convolutional transform learning. Each channel is processed by a separate 1D convolutional transform; the output of all the channels are fused by a fully connected layer of transform learning. The training procedure takes advantage of the proximal interpretation of activation functions. We apply the developed framework to multi-channel financial data for stock forecasting and trading. We compare our proposed formulation w…
Montreal Institute for Learning Algorithms（蒙特利尔学习算法研究所）；Université of Montréal（蒙特利尔大学）；Harvard University Herbaria（哈佛大学植物标本馆）；Institute for Research in Immunology and Cancer（免疫与癌症研究所）；Big Data Institute（大数据研究所）；University of Oxford（牛津大学）；University of Massachusetts Boston（马萨诸塞大学波士顿分校）
Counting objects in digital images is a process that should be replaced by machines. This tedious task is time consuming and prone to errors due to fatigue of human annotators. The goal is to have a system that takes as input an image and returns a count of the objects inside and justification for the prediction in the form of object localization. We repose a problem, originally posed by Lempitsky and Zisserman, to instead predict a count map which contains redundant counts based on the receptive field of a smaller regression network. The regression network predicts a count of the objects that…
University of Chinese Academy of Sciences（中国科学院大学）
Convolutional neural network (CNN) and its variants have led to many state-of-art results in various fields. However, a clear theoretical understanding about them is still lacking. Recently, multi-layer convolutional sparse coding (ML-CSC) has been proposed and proved to equal such simply stacked networks (plain networks). Here, we think three factors in each layer of it including the initialization, the dictionary design and the number of iterations greatly affect the performance of ML-CSC. Inspired by these considerations, we propose two novel multi-layer models--residual convolutional spars…
Training deep neural networks often requires careful hyper-parameter tuning and significant computational resources. In this paper, we propose ConvTimeNet (CTN): an off-the-shelf deep convolutional neural network (CNN) trained on diverse univariate time series classification (TSC) source tasks. Once trained, CTN can be easily adapted to new TSC target tasks via a small amount of fine-tuning using labeled instances from the target tasks. We note that the length of convolutional filters is a key aspect when building a pre-trained model that can generalize to time series of different lengths acro…
University of California at Merced（加州大学默塞德分校）；Carnegie Mellon University（卡内基梅隆大学）
Analyzing videos of human actions involves understanding the temporal relationships among video frames. State-of-the-art action recognition approaches rely on traditional optical flow estimation methods to pre-compute motion information for CNNs. Such a two-stage approach is computationally expensive, storage demanding, and not end-to-end trainable. In this paper, we present a novel CNN architecture that implicitly captures motion information between adjacent frames. We name our approach hidden two-stream CNNs because it only takes raw video frames as input and directly predicts action classes…
Despite their increasing popularity and success in a variety of supervised learning problems, deep neural networks are extremely hard to interpret and debug: Given and already trained Deep Neural Net, and a set of test inputs, how can we gain insight into how those inputs interact with different layers of the neural network? Furthermore, can we characterize a given deep neural network based on it's observed behavior on different inputs? In this paper we propose a novel factorization based approach on understanding how different deep neural networks operate. In our preliminary results, we ident…
University of Helsinki（赫尔辛基大学）；Finnish Environment Institute（芬兰环境研究所）
Semantic segmentation by convolutional neural networks (CNN) has advanced the state of the art in pixel-level classification of remote sensing images. However, processing large images typically requires analyzing the image in small patches, and hence features that have large spatial extent still cause challenges in tasks such as cloud masking. To support a wider scale of spatial features while simultaneously reducing computational requirements for large satellite images, we propose an architecture of two cascaded CNN model components successively processing undersampled and full resolution ima…
Renmin University of China（中国人民大学）；Fudan University（复旦大学）；Alibaba Group（阿里巴巴集团）
Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the {\em over-smoothing} problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}. We provide theor…
In this paper we introduce the temporally factorized 3D convolution (3TConv) as an interpretable alternative to the regular 3D convolution (3DConv). In a 3TConv the 3D convolutional filter is obtained by learning a 2D filter and a set of temporal transformation parameters, resulting in a sparse filter where the 2D slices are sequentially dependent on each other in the temporal dimension. We demonstrate that 3TConv learns temporal transformations that afford a direct interpretation. The temporal parameters can be used in combination with various existing 2D visualization methods. We also show t…
Convolutional neural networks (CNNs) have so far been the de-facto model for visual data. Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. This raises a central question: how are Vision Transformers solving these tasks? Are they acting like convolutional networks, or learning entirely different visual representations? Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more …
Recent results suggest that reinitializing a subset of the parameters of a neural network during training can improve generalization, particularly for small training sets. We study the impact of different reinitialization methods in several convolutional architectures across 12 benchmark image classification datasets, analyzing their potential gains and highlighting limitations. We also introduce a new layerwise reinitialization algorithm that outperforms previous methods and suggest explanations of the observed improved generalization. First, we show that layerwise reinitialization increases …
Amgen Inc.（安进公司）；Novartis Institutes for BioMedical Research（诺华生物医学研究所）
Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examin…
Technical University of Munich (TUM)（慕尼黑工业大学）；Kyung Hee University（庆熙大学）；University of Munich (LMU)（慕尼黑大学）
One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced. Training a model on an imbalanced dataset can introduce unique challenges to the learning problem where a model is biased towards the highly frequent class. Many methods are proposed to tackle the distributional differences and the imbalanced problem. However, the impact of these approaches on the learned features is not well studied. In this paper, we look deeper into the internal units of neural networks to observe how han…
Recent studies have shown that lung cancer screening using annual low-dose computed tomography (CT) reduces lung cancer mortality by 20% compared to traditional chest radiography. Therefore, CT lung screening has started to be used widely all across the world. However, analyzing these images is a serious burden for radiologists. The number of slices in a CT scan can be up to 600. Therefore, computer-aided-detection (CAD) systems are very important for faster and more accurate assessment of the data. In this study, we proposed a framework that analyzes CT lung screenings using convolutional neu…
Apple diseases, if not diagnosed early, can lead to massive resource loss and pose a serious threat to humans and animals who consume the infected apples. Hence, it is critical to diagnose these diseases early in order to manage plant health and minimize the risks associated with them. However, the conventional approach of monitoring plant diseases entails manual scouting and analyzing the features, texture, color, and shape of the plant leaves, resulting in delayed diagnosis and misjudgments. Our work proposes an ensembled system of Xception, InceptionResNet, and MobileNet architectures to de…
In this paper, we present an experiment on using deep learning and transfer learning techniques for emotion analysis in tweets and suggest a method to interpret our deep learning models. The proposed approach for emotion analysis combines a Long Short Term Memory (LSTM) network with a Convolutional Neural Network (CNN). Then we extend this approach for emotion intensity prediction using transfer learning technique. Furthermore, we propose a technique to visualize the importance of each word in a tweet to get a better understanding of the model. Experimentally, we show in our analysis that the …
Deep Neural Networks - especially Convolutional Neural Network (ConvNet) has become the state-of-the-art for image classification, pattern recognition and various computer vision tasks. ConvNet has a huge potential in medical domain for analyzing medical data to diagnose diseases in an efficient way. Based on extracted features by ConvNet model from MRI data, early diagnosis is very crucial for preventing progress and treating the Alzheimer's disease. Despite having the ability to deliver great performance, absence of interpretability of the model's decision can lead to misdiagnosis which can …
We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence on a quantity and distribution of interest, using an axiomatically-justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by demonstrating a number of its unique capabilities on convolutional neural networks trained on ImageNet. Our evaluation demonstrates that influence-directed …
University Politehnica of Bucharest（布加勒斯特理工大学）；Fotonation Romania, member of Xperi Group（Fotonation罗马尼亚公司（Xperi集团成员））
Emotion recognition has become an important field of research in the human-computer interactions domain. The latest advancements in the field show that combining visual with audio information lead to better results if compared to the case of using a single source of information separately. From a visual point of view, a human emotion can be recognized by analyzing the facial expression of the person. More precisely, the human emotion can be described through a combination of several Facial Action Units. In this paper, we propose a system that is able to recognize emotions with a high accuracy …
Osnabrück University（奥斯纳布吕克大学）；Osnabrück University of Applied Sciences（奥斯纳布吕克应用科学大学）
When optimizing convolutional neural networks (CNN) for a specific image-based task, specialists commonly overshoot the number of convolutional layers in their designs. By implication, these CNNs are unnecessarily resource intensive to train and deploy, with diminishing beneficial effects on the predictive performance. The features a convolutional layer can process are strictly limited by its receptive field. By layer-wise analyzing the size of the receptive fields, we can reliably predict sequences of layers that will not contribute qualitatively to the test accuracy in the given CNN architec…
CNRS（法国国家科学研究中心）；GIPSA-lab（格勒诺布尔交互物理与声学实验室）；NYU Center for Data Science（纽约大学数据科学中心）；IMB（勃艮第数学研究所）；Inria Paris（法国国家信息与自动化研究所巴黎分院）
We study properties of Graph Convolutional Networks (GCNs) by analyzing their behavior on standard models of random graphs, where nodes are represented by random latent variables and edges are drawn according to a similarity kernel. This allows us to overcome the difficulties of dealing with discrete notions such as isomorphisms on very large graphs, by considering instead more natural geometric aspects. We first study the convergence of GCNs to their continuous counterpart as the number of nodes grows. Our results are fully non-asymptotic and are valid for relatively sparse graphs with an ave…
Ulsan National Institute of Science and Technology（蔚山科学技术院）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Analyzing multivariate time series data is important for many applications such as automated control, fault diagnosis and anomaly detection. One of the key challenges is to learn latent features automatically from dynamically changing multivariate input. In visual recognition tasks, convolutional neural networks (CNNs) have been successful to learn generalized feature extractors with shared parameters over the spatial domain. However, when high-dimensional multivariate time series is given, designing an appropriate CNN model structure becomes challenging because the kernels may need to be exte…
The University of Georgia（佐治亚大学）；Innopolis University（因诺波利斯大学）
In recent years, analyzing task-based fMRI (tfMRI) data has become an essential tool for understanding brain function and networks. However, due to the sheer size of tfMRI data, its intrinsic complex structure, and lack of ground truth of underlying neural activities, modeling tfMRI data is hard and challenging. Previously proposed data-modeling methods including Independent Component Analysis (ICA) and Sparse Dictionary Learning only provided a weakly established model based on blind source separation under the strong assumption that original fMRI signals could be linearly decomposed into tim…
Case Western Reserve University（凯斯西储大学）；IBM Almaden Research Center（IBM阿尔马登研究中心）
We explore a solution for learning disease signatures from weakly, yet easily obtainable, annotated volumetric medical imaging data by analyzing 3D volumes as a sequence of 2D images. We demonstrate the performance of our solution in the detection of emphysema in lung cancer screening low-dose CT images. Our approach utilizes convolutional long short-term memory (LSTM) to "scan" sequentially through an imaging volume for the presence of disease in a portion of scanned region. This framework allowed effective learning given only volumetric images and binary disease labels, thus enabling trainin…
University of Tehran（德黑兰大学）；Yazd University（亚兹德大学）
With the social media engagement on the rise, the resulting data can be used as a rich resource for analyzing and understanding different phenomena around us. A sentiment analysis system employs these data to find the attitude of social media users towards certain entities in a given document. In this paper we propose a sentiment analysis method for Persian text using Convolutional Neural Network (CNN), a feedforward Artificial Neural Network, that categorize sentences into two and five classes (considering their intensity) by applying a layer of convolution over input data through different f…
ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks
Google（谷歌）；Florida International University（佛罗里达国际大学）；Northeastern University（东北大学）；University of California, San Diego（加州大学圣地亚哥分校）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）
China University of Petroleum - Beijing（中国石油大学（北京））；PST Service Corporation（PST服务公司）；Beijing Concord O&M Wind Power Technology Co., Ltd.（北京康科德运维风电技术有限公司）
Fractures are widely developed in hydrocarbon reservoirs and constitute the accumulation spaces and transport channels of oil and gas. Fracture detection is a fundamental task for reservoir characterization. From prestack seismic gathers, anisotropic analysis and inversion were commonly applied to characterize the dominant orientations and relative intensities of fractures. However, the existing methods were mostly based on the vertical aligned facture hypothesis, it is impossible for them to recognize fracture dip. Furthermore, it is difficult or impractical for existing methods to attain the…
Distributed coevolutionary Generative Adversarial Network (GAN) training has empirically shown success in overcoming GAN training pathologies. This is mainly due to diversity maintenance in the populations of generators and discriminators during the training process. The method studied here coevolves sub-populations on each cell of a spatial grid organized into overlapping Moore neighborhoods. We investigate the impact on the performance of two algorithm components that influence the diversity during coevolution: the performance-based selection/replacement inside each sub-population and the co…
Our formal understanding of the inductive bias that drives the success of convolutional networks on computer vision tasks is limited. In particular, it is unclear what makes hypotheses spaces born from convolution and pooling operations so suitable for natural images. In this paper we study the ability of convolutional networks to model correlations among regions of their input. We theoretically analyze convolutional arithmetic circuits, and empirically validate our findings on other types of convolutional networks as well. Correlations are formalized through the notion of separation rank, whi…
Brain-Computer Interface (BCI) system provides a pathway between humans and the outside world by analyzing brain signals which contain potential neural information. Electroencephalography (EEG) is one of most commonly used brain signals and EEG recognition is an important part of BCI system. Recently, convolutional neural networks (ConvNet) in deep learning are becoming the new cutting edge tools to tackle the problem of EEG recognition. However, training an effective deep learning model requires a big number of data, which limits the application of EEG datasets with a small number of samples.…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Facebook AI（脸书人工智能）；University of Rochester（罗切斯特大学）
Graph Convolutional Network (GCN) plays pivotal roles in many real-world applications. Despite the successes of GCN deployment, GCN often exhibits performance disparity with respect to node degrees, resulting in worse predictive accuracy for low-degree nodes. We formulate the problem of mitigating the degree-related performance disparity in GCN from the perspective of the Rawlsian difference principle, which is originated from the theory of distributive justice. Mathematically, we aim to balance the utility between low-degree nodes and high-degree nodes while minimizing the task-specific loss.…
We used convolutional neural networks (CNNs) for automatic sleep stage scoring based on single-channel electroencephalography (EEG) to learn task-specific filters for classification without using prior domain knowledge. We used an openly available dataset from 20 healthy young adults for evaluation and applied 20-fold cross-validation. We used class-balanced random sampling within the stochastic gradient descent (SGD) optimization of the CNN to avoid skewed performance in favor of the most represented sleep stages. We achieved high mean F1-score (81%, range 79-83%), mean accuracy across indivi…
KTH（瑞典皇家理工学院）；UCLA（加州大学洛杉矶分校）；Max Planck Institute for Mathematics in the Sciences（马克斯·普朗克数学研究所）；Amazon（亚马逊）
We study the family of functions that are represented by a linear convolutional neural network (LCN). These functions form a semi-algebraic subset of the set of linear maps from input space to output space. In contrast, the families of functions represented by fully-connected linear networks form algebraic sets. We observe that the functions represented by LCNs can be identified with polynomials that admit certain factorizations, and we use this perspective to describe the impact of the network's architecture on the geometry of the resulting function space. We further study the optimization of…
