Imaging phantoms are test patterns used to measure image quality in computer tomography (CT) systems. A new phantom platform (Mercury Phantom, Gammex) provides test patterns for estimating the task transfer function (TTF) or noise power spectrum (NPF) and simulates different patient sizes. Determining which image slices are suitable for analysis currently requires manual annotation of these patterns by an expert, as subtle defects may make an image unsuitable for measurement. We propose a method of automatically classifying these test patterns in a series of phantom images using deep learning techniques. By adapting a convolutional neural network based on the VGG19 architecture with weights trained on ImageNet, we use transfer learning to produce a classifier for this domain. The classifier is trained and evaluated with over 3,500 phantom images acquired at a university medical center. Input channels for color images are successfully adapted to convey contextual information for phantom images. A series of ablation studies are employed to verify design aspects of the classifier and evaluate its performance under varying training conditions. Our solution makes extensive use of image augmentation to produce a classifier that accurately classifies typical phantom images with 98% accuracy, while maintaining as much as 86% accuracy when the phantom is improperly imaged.
Convolutional neural networks (CNN) have made significant advances in hyperspectral image (HSI) classification. However, standard convolutional kernel neglects the intrinsic connections between data points, resulting in poor region delineation and small spurious predictions. Furthermore, HSIs have a unique continuous data distribution along the high dimensional spectrum domain - much remains to be addressed in characterizing the spectral contexts considering the prohibitively high dimensionality and improving reasoning capability in light of the limited amount of labelled data. This paper presents a novel architecture which explicitly addresses these two issues. Specifically, we design an architecture to encode the multiple spectral contextual information in the form of spectral pyramid of multiple embedding spaces. In each spectral embedding space, we propose graph attention mechanism to explicitly perform interpretable reasoning in the spatial domain based on the connection in spectral feature space. Experiments on three HSI datasets demonstrate that the proposed architecture can significantly improve the classification accuracy compared with the existing methods.
Representation based classification methods have become a hot research topic during the past few years, and the two most prominent approaches are sparse representation based classification (SRC) and collaborative representation based classification (CRC). CRC reveals that it is the collaborative representation rather than the sparsity that makes SRC successful. Nevertheless, the dense representation of CRC may not be discriminative which will degrade its performance for classification tasks. To alleviate this problem to some extent, we propose a new method called sparse and collaborative-competitive representation based classification (SCCRC) for image classification. Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively. Then the fused coefficient is derived by multiplying the coefficients of SRC and CCRC. Finally, the test sample is designated to the class that has the minimum residual. Experimental results on several benchmark databases demonstrate the efficacy of our proposed SCCRC. The source code of SCCRC is accessible at https://github.com/li-zi-qi/SCCRC.
We present a novel method to estimate the motion matrix between overlapping pairs of 3D views in the context of indoor scenes. We use the Manhattan world assumption to introduce lightweight geometric constraints under the form of planes into the problem, which reduces complexity by taking into account the structure of the scene. In particular, we define a stochastic framework to categorize planes as vertical or horizontal and parallel or non-parallel. We leverage this classification to match pairs of planes in overlapping views with point-of-view agnostic structural metrics. We propose to split the motion computation using the classification and estimate separately the rotation and translation of the sensor, using a quadric minimizer. We validate our approach on a toy example and present quantitative experiments on a public RGB-D dataset, comparing against recent state-of-the-art methods. Our evaluation shows that planar constraints only add low computational overhead while improving results in precision when applied after a prior coarse estimate. We conclude by giving hints towards extensions and improvements of current results.
In the past few years, convolutional neural networks (CNNs) have achieved impressive results in computer vision tasks, which however mainly focus on photos with natural scene content. Besides, non-sensor derived images such as illustrations, data visualizations, figures, etc. are typically used to convey complex information or to explore large datasets. However, this kind of images has received little attention in computer vision. CNNs and similar techniques use large volumes of training data. Currently, many document analysis systems are trained in part on scene images due to the lack of large datasets of educational image data. In this paper, we address this issue and present SlideImages, a dataset for the task of classifying educational illustrations. SlideImages contains training data collected from various sources, e.g., Wikimedia Commons and the AI2D dataset, and test data collected from educational slides. We have reserved all the actual educational images as a test dataset in order to ensure that the approaches using this dataset generalize well to new educational images, and potentially other domains. Furthermore, we present a baseline system using a standard deep neural architecture and discuss dealing with the challenge of limited training data.
After four decades of research there still exists a Classification accuracy gap of about 20% between our best Unsupervisedly Learned Representations methods and the accuracy rates achieved by intelligent animals. It thus may well be that we are looking in the wrong direction. A possible solution to this puzzle is presented. We demonstrate that Reinforcement Learning can learn representations which achieve the same accuracy as that of animals. Our main modest contribution lies in the observations that: a. when applied to a real world environment Reinforcement Learning does not require labels, and thus may be legitimately considered as Unsupervised Learning, and b. in contrast, when Reinforcement Learning is applied in a simulated environment it does inherently require labels and should thus be generally be considered as Supervised Learning. The corollary of these observations is that further search for Unsupervised Learning competitive paradigms which may be trained in simulated environments may be futile.
Interferometric Synthetic Aperture Radar (InSAR) imagery based on microwaves reflected off ground targets is becoming increasingly important in remote sensing for ground movement estimation. However, the reflections are contaminated by noise, which distorts the signal's wrapped phase. Demarcation of image regions based on degree of contamination ("coherence") is an important component of the InSAR processing pipeline. We introduce Convolutional Neural Networks (CNNs) to this problem domain and show their effectiveness in improving coherence-based demarcation and reducing misclassifications in completely incoherent regions through intelligent preprocessing of training data. Quantitative and qualitative comparisons prove superiority of proposed method over three established methods.
Classifiers built with neural networks handle large-scale high dimensional data, such as facial images from computer vision, extremely well while traditional statistical methods often fail miserably. In this paper, we attempt to understand this empirical success in high dimensional classification by deriving the convergence rates of excess risk. In particular, a teacher-student framework is proposed that assumes the Bayes classifier to be expressed as ReLU neural networks. In this setup, we obtain a sharp rate of convergence, i.e., $\tilde{O}_d(n^{-2/3})$, for classifiers trained using either 0-1 loss or hinge loss. This rate can be further improved to $\tilde{O}_d(n^{-1})$ when the data distribution is separable. Here, $n$ denotes the sample size. An interesting observation is that the data dimension only contributes to the $\log(n)$ term in the above rates. This may provide one theoretical explanation for the empirical successes of deep neural networks in high dimensional classification, particularly for structured data.
The aim of this work is to propose a meta-algorithm for automatic classification in the presence of discrete binary classes. Classifier learning in the presence of overlapping class distributions is a challenging problem in machine learning. Overlapping classes are described by the presence of ambiguous areas in the feature space with a high density of points belonging to both classes. This often occurs in real-world datasets, one such example is numeric data denoting properties of particle decays derived from high-energy accelerators like the Large Hadron Collider (LHC). A significant body of research targeting the class overlap problem use ensemble classifiers to boost the performance of algorithms by using them iteratively in multiple stages or using multiple copies of the same model on different subsets of the input training data. The former is called boosting and the latter is called bagging. The algorithm proposed in this thesis targets a challenging classification problem in high energy physics - that of improving the statistical significance of the Higgs discovery. The underlying dataset used to train the algorithm is experimental data built from the official ATLAS full-detector simulation with Higgs events (signal) mixed with different background events (background) that closely mimic the statistical properties of the signal generating class overlap. The algorithm proposed is a variant of the classical boosted decision tree which is known to be one of the most successful analysis techniques in experimental physics. The algorithm utilizes a unified framework that combines two meta-learning techniques - bagging and boosting. The results show that this combination only works in the presence of a randomization trick in the base learners.
In this paper, we introduce a neural network framework for semi-supervised clustering (SSC) with pairwise (must-link or cannot-link) constraints. In contrast to existing approaches, we decompose SSC into two simpler classification tasks/stages: the first stage uses a pair of Siamese neural networks to label the unlabeled pairs of points as must-link or cannot-link; the second stage uses the fully pairwise-labeled dataset produced by the first stage in a supervised neural-network-based clustering method. The proposed approach, S3C2 (Semi-Supervised Siamese Classifiers for Clustering), is motivated by the observation that binary classification (such as assigning pairwise relations) is usually easier than multi-class clustering with partial supervision. On the other hand, being classification-based, our method solves only well-defined classification problems, rather than less well specified clustering tasks. Extensive experiments on various datasets demonstrate the high performance of the proposed method.
Aggregated hold-out (Agghoo) is a method which averages learning rules selected by hold-out (that is, cross-validation with a single split). We provide the first theoretical guarantees on Agghoo, ensuring that it can be used safely: Agghoo performs at worst like the hold-out when the risk is convex. The same holds true in classification with the 0-1 risk, with an additional constant factor. For the hold-out, oracle inequalities are known for bounded losses, as in binary classification. We show that similar results can be proved, under appropriate assumptions, for other risk-minimization problems. In particular, we obtain an oracle inequality for regularized kernel regression with a Lip-schitz loss, without requiring that the Y variable or the regressors be bounded. Numerical experiments show that aggregation brings a significant improvement over the hold-out and that Agghoo is competitive with cross-validation.
Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with "task descriptions" in natural language (e.g., Radford et al., 2019). While this approach underperforms its supervised counterpart, we show in this work that the two ideas can be combined: We introduce Pattern-Exploiting Training (PET), a semi-supervised training procedure that reformulates input examples as cloze-style phrases to help language models understand a given task. These phrases are then used to assign soft labels to a large set of unlabeled examples. Finally, standard supervised training is performed on the resulting training set. For several tasks and languages, PET outperforms supervised training and strong semi-supervised approaches in low-resource settings by a large margin.
Time series motifs play an important role in the time series analysis. The motif-based time series clustering is used for the discovery of higher-order patterns or structures in time series data. Inspired by the convolutional neural network (CNN) classifier based on the image representations of time series, motif difference field (MDF) is proposed. Compared to other image representations of time series, MDF is simple and easy to construct. With the Fully Convolution Network (FCN) as the classifier, MDF demonstrates the superior performance on the UCR time series dataset in benchmark with other time series classification methods. It is interesting to find that the triadic time series motifs give the best result in the test. Due to the motif clustering reflected in MDF, the significant motifs are detected with the help of the Gradient-weighted Class Activation Mapping (Grad-CAM). The areas in MDF with high weight in Grad-CAM have a high contribution from the significant motifs with the desired ordinal patterns associated with the signature patterns in time series. However, the signature patterns cannot be identified with the neural network classifiers directly based on the time series.
Wikipedia is a huge opportunity for machine learning, being the largest semi-structured base of knowledge available. Because of this, many works examine its contents, and focus on structuring it in order to make it usable in learning tasks, for example by classifying it into an ontology. Beyond its textual contents, Wikipedia also displays a typical graph structure, where pages are linked together through citations. In this paper, we address the task of integrating graph (i.e. structure) information to classify Wikipedia into a fine-grained named entity ontology (NE), the Extended Named Entity hierarchy. To address this task, we first start by assessing the relevance of the graph structure for NE classification. We then explore two directions, one related to feature vectors using graph descriptors commonly used in large-scale network analysis, and one extending flat classification to a weighted model taking into account semantic similarity. We conduct at-scale practical experiments, on a manually labeled subset of 22,000 pages extracted from the Japanese Wikipedia. Our results show that integrating graph information succeeds at reducing sparsity of the input feature space, and yields classification results that are comparable or better than previous works.
Epilepsy affects nearly 1% of the global population, of which two thirds can be treated by anti-epileptic drugs and a much lower percentage by surgery. Diagnostic procedures for epilepsy and monitoring are highly specialized and labour-intensive. The accuracy of the diagnosis is also complicated by overlapping medical symptoms, varying levels of experience and inter-observer variability among clinical professions. This paper proposes a novel hybrid bilinear deep learning network with an application in the clinical procedures of epilepsy classification diagnosis, where the use of surface electroencephalogram (sEEG) and audiovisual monitoring is standard practice. Hybrid bilinear models based on two types of feature extractors, namely Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), are trained using Short-Time Fourier Transform (STFT) of one-second sEEG. In the proposed hybrid models, CNNs extract spatio-temporal patterns, while RNNs focus on the characteristics of temporal dynamics in relatively longer intervals given the same input data. Second-order features, based on interactions between these spatio-temporal features are further explored by bilinear pooling and used for epilepsy classification. Our proposed methods obtain an F1-score of 97.4% on the Temple University Hospital Seizure Corpus and 97.2% on the EPILEPSIAE dataset, comparing favourably to existing benchmarks for sEEG-based seizure type classification. The open-source implementation of this study is available at https://github.com/NeuroSyd/Epileptic-Seizure-Classification
Recent studies in image classification have demonstrated a variety of techniques for improving the performance of Convolutional Neural Networks (CNNs). However, attempts to combine existing techniques to create a practical model are still uncommon. In this study, we carry out extensive experiments to validate that carefully assembling these techniques and applying them to basic CNN models (e.g. ResNet and MobileNet) can improve the accuracy and robustness of the models while minimizing the loss of throughput. Our proposed assembled ResNet-50 shows improvements in top-1 accuracy from 76.3\% to 82.78\%, mCE from 76.0\% to 48.9\% and mFR from 57.7\% to 32.3\% on ILSVRC2012 validation set. With these improvements, inference throughput only decreases from 536 to 312. To verify the performance improvement in transfer learning, fine grained classification and image retrieval tasks were tested on several public datasets and showed that the improvement to backbone network performance boosted transfer learning performance significantly. Our approach achieved 1st place in the iFood Competition Fine-Grained Visual Recognition at CVPR 2019, and the source code and trained models are available at https://github.com/clovaai/assembled-cnn
In this paper we consider authentication at the physical layer, in which the authenticator aims at distinguishing a legitimate supplicant from an attacker on the basis of the characteristics of a set of parallel wireless channels, which are affected by time-varying fading. Moreover, the attacker's channel has a spatial correlation with the supplicant's one. In this setting, we assess and compare the performance achieved by different approaches under different channel conditions. We first consider the use of two different statistical decision methods, and we prove that using a large number of references (in the form of channel estimates) affected by different levels of time-varying fading is not beneficial from a security point of view. We then consider classification methods based on machine learning. In order to face the worst case scenario of an authenticator provided with no forged messages during training, we consider one-class classifiers. When instead the training set includes some forged messages, we resort to more conventional binary classifiers, considering the cases in which such messages are either labelled or not. For the latter case, we exploit clustering algorithms to label the training set. The performance of both nearest neighbor (NN) and support vector machine (SVM) classification techniques is evaluated. Through numerical examples, we show that under the same probability of false alarm, one-class classification (OCC) algorithms achieve the lowest probability of missed detection when a small spatial correlation exists between the main channel and the adversary one, while statistical methods are advantageous when the spatial correlation between the two channels is large.
A robust theoretical framework that can describe and predict the generalization ability of deep neural networks (DNNs) in general circumstances remains elusive. Classical attempts have produced complexity metrics that rely heavily on global measures of compactness and capacity with little investigation into the effects of sub-component collaboration. We demonstrate intriguing regularities in the activation patterns of the hidden nodes within fully-connected feedforward networks. By tracing the origin of these patterns, we show how such networks can be viewed as the combination of two information processing systems: one continuous and one discrete. We describe how these two systems arise naturally from the gradient-based optimization process, and demonstrate the classification ability of the two systems, individually and in collaboration. This perspective on DNN classification offers a novel way to think about generalization, in which different subsets of the training data are used to train distinct classifiers; those classifiers are then combined to perform the classification task, and their consistency is crucial for accurate classification.
In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures. Recent works often solve this problem via advanced graph convolution in a conventionally supervised manner, but the performance could degrade significantly when labeled data is scarce. To this end, we propose a Graph Inference Learning (GIL) framework to boost the performance of semi-supervised node classification by learning the inference of node labels on graph topology. To bridge the connection between two nodes, we formally define a structure relation by encapsulating node attributes, between-node paths, and local topological structures together, which can make the inference conveniently deduced from one node to another node. For learning the inference process, we further introduce meta-optimization on structure relations from training nodes to validation nodes, such that the learnt graph inference capability can be better self-adapted to testing nodes. Comprehensive evaluations on four benchmark datasets (including Cora, Citeseer, Pubmed, and NELL) demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods on the semi-supervised node classification task.
Algorithmic fairness involves expressing notions such as equity, or reasonable treatment, as quantifiable measures that a machine learning algorithm can optimise. Most work in the literature to date has focused on classification problems where the prediction is categorical, such as accepting or rejecting a loan application. This is in part because classification fairness measures are easily computed by comparing the rates of outcomes, leading to behaviours such as ensuring that the same fraction of eligible men are selected as eligible women. But such measures are computationally difficult to generalise to the continuous regression setting for problems such as pricing, or allocating payments. The difficulty arises from estimating conditional densities (such as the probability density that a system will over-charge by a certain amount). For the regression setting we introduce tractable approximations of the independence, separation and sufficiency criteria by observing that they factorise as ratios of different conditional probabilities of the protected attributes. We introduce and train machine learning classifiers, distinct from the predictor, as a mechanism to estimate these probabilities from the data. This naturally leads to model agnostic, tractable approximations of the criteria, which we explore experimentally.