In this paper, we investigate the problem of classifying feature vectors with mutually independent but non-identically distributed elements. First, we show the importance of this problem. Next, we propose a classifier and derive an analytical upper bound on its error probability. We show that the error probability goes to zero as the length of the feature vectors grows, even when there is only one training feature vector per label available. Thereby, we show that for this important problem at least one asymptotically optimal classifier exists. Finally, we provide numerical examples where we show that the performance of the proposed classifier outperforms conventional classification algorithms when the number of training data is small and the length of the feature vectors is sufficiently high.
In this paper, a Multi-Scale Fully Convolutional Network (MSFCN) with multi-scale convolutional kernel is proposed to exploit discriminative representations from two-dimensional (2D) satellite images.
This technical report summarizes submissions and compiles from Actor-Action video classification challenge held as a final project in CSC 249/449 Machine Vision course (Spring 2020) at University of Rochester
In this paper, we propose a domain adaptation framework to address the device mismatch issue in acoustic scene classification leveraging upon neural label embedding (NLE) and relational teacher student learning (RTSL). Taking into account the structural relationships between acoustic scene classes, our proposed framework captures such relationships which are intrinsically device-independent. In the training stage, transferable knowledge is condensed in NLE from the source domain. Next in the adaptation stage, a novel RTSL strategy is adopted to learn adapted target models without using paired source-target data often required in conventional teacher student learning. The proposed framework is evaluated on the DCASE 2018 Task1b data set. Experimental results based on AlexNet-L deep classification models confirm the effectiveness of our proposed approach for mismatch situations. NLE-alone adaptation compares favourably with the conventional device adaptation and teacher student based adaptation techniques. NLE with RTSL further improves the classification accuracy.
In this paper, we propose a sub-utterance unit selection framework to remove acoustic segments in audio recordings that carry little information for acoustic scene classification (ASC). Our approach is built upon a universal set of acoustic segment units covering the overall acoustic scene space. First, those units are modeled with acoustic segment models (ASMs) used to tokenize acoustic scene utterances into sequences of acoustic segment units. Next, paralleling the idea of stop words in information retrieval, stop ASMs are automatically detected. Finally, acoustic segments associated with the stop ASMs are blocked, because of their low indexing power in retrieval of most acoustic scenes. In contrast to building scene models with whole utterances, the ASM-removed sub-utterances, i.e., acoustic utterances without stop acoustic segments, are then used as inputs to the AlexNet-L back-end for final classification. On the DCASE 2018 dataset, scene classification accuracy increases from 68%, with whole utterances, to 72.1%, with segment selection. This represents a competitive accuracy without any data augmentation, and/or ensemble strategy. Moreover, our approach compares favourably to AlexNet-L with attention.
Noisy pairwise comparison feedback has been incorporated to improve the overall query complexity of interactively learning binary classifiers. The \textit{positivity comparison oracle} is used to provide feedback on which is more likely to be positive given a pair of data points. Because it is impossible to infer accurate labels using this oracle alone \textit{without knowing the classification threshold}, existing methods still rely on the traditional \textit{explicit labeling oracle}, which directly answers the label given a data point. Existing methods conduct sorting on all data points and use explicit labeling oracle to find the classification threshold. The current methods, however, have two drawbacks: (1) they needs unnecessary sorting for label inference; (2) quick sort is naively adapted to noisy feedback and negatively affects practical performance. In order to avoid this inefficiency and acquire information of the classification threshold, we propose a new pairwise comparison oracle concerning uncertainties. This oracle receives two data points as input and answers which one has higher uncertainty. We then propose an efficient adaptive labeling algorithm using the proposed oracle and the positivity comparison oracle. In addition, we also address the situation where the labeling budget is insufficient compared to the dataset size, which can be dealt with by plugging the proposed algorithm into an active learning algorithm. Furthermore, we confirm the feasibility of the proposed oracle and the performance of the proposed algorithm theoretically and empirically.
Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within local patches. However, for each pixel in an HSI, it is not only related to its nearby pixels but also has connections to pixels far away from itself. Therefore, to incorporate the long-range contextual information, a deep fully convolutional network (FCN) with an efficient non-local module, named ENL-FCN, is proposed for HSI classification. In the proposed framework, a deep FCN considers an entire HSI as input and extracts spectral-spatial information in a local receptive field. The efficient non-local module is embedded in the network as a learning unit to capture the long-range contextual information. Different from the traditional non-local neural networks, the long-range contextual information is extracted in a specially designed criss-cross path for computation efficiency. Furthermore, by using a recurrent operation, each pixel's response is aggregated from all pixels of HSI. The benefits of our proposed ENL-FCN are threefold: 1) the long-range contextual information is incorporated effectively, 2) the efficient module can be freely embedded in a deep neural network in a plug-and-play fashion, and 3) it has much fewer learning parameters and requires less computational resources. The experiments conducted on three popular HSI datasets demonstrate that the proposed method achieves state-of-the-art classification performance with lower computational cost in comparison with several leading deep neural networks for HSI.
Opinion mining on social media posts has become more and more popular. Users often express their opinion on a topic not only with words but they also use image symbols such as emoticons and emoji. In this paper, we investigate the effect of emoji-based features in opinion classification of Uzbek texts, and more specifically movie review comments from YouTube. Several classification algorithms are tested, and feature ranking is performed to evaluate the discriminative ability of the emoji-based features.
Quantifying the characteristics of public attention is an essential prerequisite for appropriate crisis management during severe events such as pandemics. For this purpose, we propose language-agnostic tweet representations to perform large-scale Twitter discourse classification with machine learning. Our analysis on more than 26 million COVID-19 tweets shows that large-scale surveillance of public discourse is feasible with computationally lightweight classifiers by out-of-the-box utilization of these representations.
Spatial attention has been introduced to convolutional neural networks (CNNs) for improving both their performance and interpretability in visual tasks including image classification. The essence of the spatial attention is to learn a weight map which represents the relative importance of activations within the same layer or channel. All existing attention mechanisms are local attentions in the sense that weight maps are image-specific. However, in the medical field, there are cases that all the images should share the same weight map because the set of images record the same kind of symptom related to the same object and thereby share the same structural content. In this paper, we thus propose a novel global spatial attention mechanism in CNNs mainly for medical image classification. The global weight map is instantiated by a decision boundary between important pixels and unimportant pixels. And we propose to realize the decision boundary by a binary classifier in which the intensities of all images at a pixel are the features of the pixel. The binary classification is integrated into an image classification CNN and is to be optimized together with the CNN. Experiments on two medical image datasets and one facial expression dataset showed that with the proposed attention, not only the performance of four powerful CNNs which are GoogleNet, VGG, ResNet, and DenseNet can be improved, but also meaningful attended regions can be obtained, which is beneficial for understanding the content of images of a domain.
There are extensive researches focusing on automated diabetic reti-nopathy (DR) detection from fundus images. However, the accuracy drop is ob-served when applying these models in real-world DR screening, where the fun-dus camera brands are different from the ones used to capture the training im-ages. How can we train a classification model on labeled fundus images ac-quired from only one camera brand, yet still achieves good performance on im-ages taken by other brands of cameras? In this paper, we quantitatively verify the impact of fundus camera brands related domain shift on the performance of DR classification models, from an experimental perspective. Further, we pro-pose camera-oriented residual-CycleGAN to mitigate the camera brand differ-ence by domain adaptation and achieve increased classification performance on target camera images. Extensive ablation experiments on both the EyePACS da-taset and a private dataset show that the camera brand difference can signifi-cantly impact the classification performance and prove that our proposed meth-od can effectively improve the model performance on the target domain. We have inferred and labeled the camera brand for each image in the EyePACS da-taset and will publicize the camera brand labels for further research on domain adaptation.
In addition to the ongoing development, pre-salt carbonate reservoir characterization remains a challenge, primarily due to inherent geological particularities. These challenges stimulate the use of well-established technologies, such as artificial intelligence algorithms, for image classification tasks. Therefore, this work intends to present an application of deep learning techniques to identify patterns in Brazilian pre-salt carbonate rock microtomographic images, thus making possible lithological classification. Four convolutional neural network models were proposed. The first model includes three convolutional layers followed by fully connected layers and is used as a base model for the following proposals. In the next two models, we replace the max pooling layer with a spatial pyramid pooling and a global average pooling layer. The last model uses a combination of spatial pyramid pooling followed by global average pooling in place of the last pooling layer. All models are compared using original images, when possible, as well as resized images. The dataset consists of 6,000 images from three different classes. The model performances were evaluated by each image individually, as well as by the most frequently predicted class for each sample. According to accuracy, Model 2 trained on resized images achieved the best results, reaching an average of 75.54% for the first evaluation approach and an average of 81.33% for the second. We developed a workflow to automate and accelerate the lithology classification of Brazilian pre-salt carbonate samples by categorizing microtomographic images using deep learning algorithms in a non-destructive way.
Automated breast ultrasound (ABUS) is a new and promising imaging modality for breast cancer detection and diagnosis, which could provide intuitive 3D information and coronal plane information with great diagnostic value. However, manually screening and diagnosing tumors from ABUS images is very time-consuming and overlooks of abnormalities may happen. In this study, we propose a novel two-stage 3D detection network for locating suspected lesion areas and further classifying lesions as benign or malignant tumors. Specifically, we propose a 3D detection network rather than frequently-used segmentation network to locate lesions in ABUS images, thus our network can make full use of the spatial context information in ABUS images. A novel similarity loss is designed to effectively distinguish lesions from background. Then a classification network is employed to identify the located lesions as benign or malignant. An IoU-balanced classification loss is adopted to improve the correlation between classification and localization task. The efficacy of our network is verified from a collected dataset of 418 patients with 145 benign tumors and 273 malignant tumors. Experiments show our network attains a sensitivity of 97.66% with 1.23 false positives (FPs), and has an area under the curve(AUC) value of 0.8720.
An adequate classification of proximal femur fractures from X-ray images is crucial for the treatment choice and the patients' clinical outcome. We rely on the commonly used AO system, which describes a hierarchical knowledge tree classifying the images into types and subtypes according to the fracture's location and complexity. In this paper, we propose a method for the automatic classification of proximal femur fractures into 3 and 7 AO classes based on a Convolutional Neural Network (CNN). As it is known, CNNs need large and representative datasets with reliable labels, which are hard to collect for the application at hand. In this paper, we design a curriculum learning (CL) approach that improves over the basic CNNs performance under such conditions. Our novel formulation reunites three curriculum strategies: individually weighting training samples, reordering the training set, and sampling subsets of data. The core of these strategies is a scoring function ranking the training samples. We define two novel scoring functions: one from domain-specific prior knowledge and an original self-paced uncertainty score. We perform experiments on a clinical dataset of proximal femur radiographs. The curriculum improves proximal femur fracture classification up to the performance of experienced trauma surgeons. The best curriculum method reorders the training set based on prior knowledge resulting into a classification improvement of 15%. Using the publicly available MNIST dataset, we further discuss and demonstrate the benefits of our unified CL formulation for three controlled and challenging digit recognition scenarios: with limited amounts of data, under class-imbalance, and in the presence of label noise. The code of our work is available at: https://github.com/ameliajimenez/curriculum-learning-prior-uncertainty.
In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.
The advancement of technology in Quantum Computing has brought possibilities for the execution of algorithms in real quantum devices. However, the existing errors in the current quantum hardware and the low number of available qubits make it necessary to use solutions that use fewer qubits and fewer operations, mitigating such obstacles. Hadamard Classifier (HC) is a distance-based quantum machine learning model for pattern recognition. We present a new classifier based on HC named Quantum One-class Classifier (QOCC) that consists of a minimal quantum machine learning model with fewer operations and qubits, thus being able to mitigate errors from NISQ (Noisy Intermediate-Scale Quantum) computers. Experimental results were obtained by running the proposed classifier on a quantum device and show that QOCC has advantages over HC.
Rainfall prediction helps planners anticipate potential social and economic impacts produced by too much or too little rain. This research investigates a class-based approach to rainfall prediction from 1-30 days in advance. The study made regional predictions based on sequences of daily rainfall maps of the continental US, with rainfall quantized at 3 levels: light or no rain; moderate; and heavy rain. Three regions were selected, corresponding to three squares from a $5\times5$ grid covering the map area. Rainfall predictions up to 30 days ahead for these three regions were based on a support vector machine (SVM) applied to consecutive sequences of prior daily rainfall map images. The results show that predictions for corner squares in the grid were less accurate than predictions obtained by a simple untrained classifier. However, SVM predictions for a central region outperformed the other two regions, as well as the untrained classifier. We conclude that there is some evidence that SVMs applied to large-scale precipitation maps can under some conditions give useful information for predicting regional rainfall, but care must be taken to avoid pitfall
This paper presents an experimental analysis about trade-offs in top-k classification accuracies on losses for deep leaning and proposal of a novel top-k loss. Commonly-used cross entropy (CE) is not guaranteed to optimize top-k prediction without infinite training data and model complexities. The objective is to clarify when CE sacrifices top-k accuracies to optimize top-1 prediction, and to design loss that improve top-k accuracy under such conditions. Our novel loss is basically CE modified by grouping temporal top-k classes as a single class. To obtain a robust decision boundary, we introduce an adaptive transition from normal CE to our loss, and thus call it top-k transition loss. It is demonstrated that CE is not always the best choice to learn top-k prediction in our experiments. First, we explore trade-offs between top-1 and top-k (=2) accuracies on synthetic datasets, and find a failure of CE in optimizing top-k prediction when we have complex data distribution for a given model to represent optimal top-1 prediction. Second, we compare top-k accuracies on CIFAR-100 dataset targeting top-5 prediction in deep learning. While CE performs the best in top-1 accuracy, in top-5 accuracy our loss performs better than CE except using one experimental setup. Moreover, our loss has been found to provide better top-k accuracies compared to CE at k larger than 10. As a result, a ResNet18 model trained with our loss reaches 99 % accuracy with k=25 candidates, which is a smaller candidate number than that of CE by 8.
In cross-lingual text classification, one seeks to exploit labeled data from one language to train a text classification model that can then be applied to a completely different language. Recent multilingual representation models have made it much easier to achieve this. Still, there may still be subtle differences between languages that are neglected when doing so. To address this, we present a semi-supervised adversarial training process that minimizes the maximal loss for label-preserving input perturbations. The resulting model then serves as a teacher to induce labels for unlabeled target language samples that can be used during further adversarial training, allowing us to gradually adapt our model to the target language. Compared with a number of strong baselines, we observe significant gains in effectiveness on document and intent classification for a diverse set of languages.
Multi-label zero-shot classification aims to predict multiple unseen class labels for an input image. It is more challenging than its single-label counterpart. On one hand, the unconstrained number of labels assigned to each image makes the model more easily overfit to those seen classes. On the other hand, there is a large semantic gap between seen and unseen classes in the existing multi-label classification datasets. To address these difficult issues, this paper introduces a novel multi-label zero-shot classification framework by learning to transfer from external knowledge. We observe that ImageNet is commonly used to pretrain the feature extractor and has a large and fine-grained label space. This motivates us to exploit it as external knowledge to bridge the seen and unseen classes and promote generalization. Specifically, we construct a knowledge graph including not only classes from the target dataset but also those from ImageNet. Since ImageNet labels are not available in the target dataset, we propose a novel PosVAE module to infer their initial states in the extended knowledge graph. Then we design a relational graph convolutional network (RGCN) to propagate information among classes and achieve knowledge transfer. Experimental results on two benchmark datasets demonstrate the effectiveness of the proposed approach.