Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is challenging, and even the best approaches show much weaker performance than their supervised counterparts. Self-supervised deep learning has become a strong instrument for representation learning in computer vision. However, those methods have not been evaluated in a fully unsupervised setting. In this paper, we propose a simple scheme for unsupervised classification based on self-supervised representations. We evaluate the proposed approach with several recent self-supervised methods showing that it achieves competitive results for ImageNet classification (39% accuracy on ImageNet with 1000 clusters and 46% with overclustering). We suggest adding the unsupervised evaluation to a set of standard benchmarks for self-supervised learning. The code is available at https://github.com/Randl/kmeans_selfsuper
Deep learning based approaches to Computer Aided Diagnosis (CAD) typically pose the problem as an image classification (Normal or Abnormal) problem. These systems achieve high to very high accuracy in specific disease detection for which they are trained but lack in terms of an explanation for the provided decision/classification result. The activation maps which correspond to decisions do not correlate well with regions of interest for specific diseases. This paper examines this problem and proposes an approach which mimics the clinical practice of looking for an evidence prior to diagnosis. A CAD model is learnt using a mixed set of information: class labels for the entire training set of images plus a rough localisation of suspect regions as an extra input for a smaller subset of training images for guiding the learning. The proposed approach is illustrated with detection of diabetic macular edema (DME) from OCT slices. Results of testing on on a large public dataset show that with just a third of images with roughly segmented fluid filled regions, the classification accuracy is on par with state of the art methods while providing a good explanation in the form of anatomically accurate heatmap /region of interest. The proposed solution is then adapted to Breast Cancer detection from mammographic images. Good evaluation results on public datasets underscores the generalisability of the proposed solution.
Conditional Maximum Mean Discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions, thus it has been successfully used for pattern classification. However, CMMD does not work well on complex distributions, especially when the kernel function fails to correctly characterize the difference between intra-class similarity and inter-class similarity. In this paper, a new kernel learning method is proposed to improve the discrimination performance of CMMD. It can be operated with deep network features iteratively and thus denoted as KLN for abbreviation. The CMMD loss and an auto-encoder (AE) are used to learn an injective function. By considering the compound kernel, i.e., the injective function with a characteristic kernel, the effectiveness of CMMD for data category description is enhanced. KLN can simultaneously learn a more expressive kernel and label prediction distribution, thus, it can be used to improve the classification performance in both supervised and semi-supervised learning scenarios. In particular, the kernel-based similarities are iteratively learned on the deep network features, and the algorithm can be implemented in an end-to-end manner. Extensive experiments are conducted on four benchmark datasets, including MNIST, SVHN, CIFAR-10 and CIFAR-100. The results indicate that KLN achieves state-of-the-art classification performance.
This paper presents a wide-area event classification in transmission power grids. The deep neural network (DNN) based classifier is developed based on the availability of data from time-synchronized phasor measurement units (PMUs). The proposed DNN is trained using Bayesian optimization to search for the best hyperparameters. The effectiveness of the proposed event classification is validated through the real-world dataset of the U.S. transmission grids. This dataset includes line outage, transformer outage, frequency event, and oscillation events. The validation process also includes different PMU outputs, such as voltage magnitude, angle, current magnitude, frequency, and rate of change of frequency (ROCOF). The simulation results show that ROCOF as input feature gives the best classification performance. In addition, it is shown that the classifier trained with higher sampling rate PMUs and a larger dataset has higher accuracy.
Image set recognition has been widely applied in many practical problems like real-time video retrieval and image caption tasks. Due to its superior performance, it has grown into a significant topic in recent years. However, images with complicated variations, e.g., postures and human ages, are difficult to address, as these variations are continuous and gradual with respect to image appearance. Consequently, the crucial point of image set recognition is to mine the intrinsic connection or structural information from the image batches with variations. In this work, a Discriminant Residual Analysis (DRA) method is proposed to improve the classification performance by discovering discriminant features in related and unrelated groups. Specifically, DRA attempts to obtain a powerful projection which casts the residual representations into a discriminant subspace. Such a projection subspace is expected to magnify the useful information of the input space as much as possible, then the relation between the training set and the test set described by the given metric or distance will be more precise in the discriminant subspace. We also propose a nonfeasance strategy by defining another approach to construct the unrelated groups, which help to reduce furthermore the cost of sampling errors. Two regularization approaches are used to deal with the probable small sample size problem. Extensive experiments are conducted on benchmark databases, and the results show superiority and efficiency of the new methods.
Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we propose a new paradigm of unsupervised few-shot learning to repair the deficiencies. We solve the few-shot tasks in two phases: meta-training a transferable feature extractor via contrastive self-supervised learning and training a classifier using graph aggregation, self-distillation and manifold augmentation. Once meta-trained, the model can be used in any type of tasks with a task-dependent classifier training. Our method achieves state of-the-art performance in a variety of established few-shot tasks on the standard few-shot visual classification datasets, with an 8- 28% increase compared to the available unsupervised few-shot learning methods.
Classification of datasets into two or more distinct classes is an important machine learning task. Many methods are able to classify binary classification tasks with a very high accuracy on test data, but cannot provide any easily interpretable explanation for users to have a deeper understanding of reasons for the split of data into two classes. In this paper, we highlight and evaluate a recently proposed nonlinear decision tree approach with a number of commonly used classification methods on a number of datasets involving a few to a large number of features. The study reveals key issues such as effect of classification on the method's parameter values, complexity of the classifier versus achieved accuracy, and interpretability of resulting classifiers.
The paper proposes to employ deep convolutional neural networks (CNNs) to classify noncoding RNA (ncRNA) sequences. To this end, we first propose an efficient approach to convert the RNA sequences into images characterizing their base-pairing probability. As a result, classifying RNA sequences is converted to an image classification problem that can be efficiently solved by available CNN-based classification models. The paper also considers the folding potential of the ncRNAs in addition to their primary sequence. Based on the proposed approach, a benchmark image classification dataset is generated from the RFAM database of ncRNA sequences. In addition, three classical CNN models have been implemented and compared to demonstrate the superior performance and efficiency of the proposed approach. Extensive experimental results show the great potential of using deep learning approaches for RNA classification.
Jet flavour classification is of paramount importance for a broad range of applications in modern-day high-energy-physics experiments, particularly at the LHC. In this paper we propose a novel architecture for this task that exploits modern deep learning techniques. This new model, called DeepJet, overcomes the limitations in input size that affected previous approaches. As a result, the heavy flavour classification performance improves, and the model is extended to also perform quark-gluon tagging.
Privacy issues were raised in the process of training deep learning in medical, mobility, and other fields. To solve this problem, we present privacy-preserving distributed deep learning method that allow clients to learn a variety of data without direct exposure. We divided a single deep learning architecture into a common extractor, a cloud model and a local classifier for the distributed learning. First, the common extractor, which is used by local clients, extracts secure features from the input data. The secure features also take the role that the cloud model can employ various task and diverse types of data. The feature contain the most important information that helps to proceed various task. Second, the cloud model including most parts of the whole training model gets the embedded features from the massive local clients, and performs most of deep learning operations which takes severe computing cost. After the operations in cloud model finished, outputs of the cloud model send back to local clients. Finally, the local classifier determined classification results and delivers the results to local clients. When clients train models, our model does not directly expose sensitive information to exterior network. During the test, the average performance improvement was 2.63% over the existing local training model. However, in a distributed environment, there is a possibility of inversion attack due to exposed features. For this reason, we experimented with the common extractor to prevent data restoration. The quality of restoration of the original image was tested by adjusting the depth of the common extractor. As a result, we found that the deeper the common extractor, the restoration score decreased to 89.74.
This report describes the methods employed by the Democritus University of Thrace (DUTH) team for participating in SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles. Our team dealt with Subtask 2: Technique Classification. We used shallow Natural Language Processing (NLP) preprocessing techniques to reduce the noise in the dataset, feature selection methods, and common supervised machine learning algorithms. Our final model is based on using the BERT system with entity mapping. To improve our model's accuracy, we mapped certain words into five distinct categories by employing word-classes and entity recognition.
Class imbalance is a common problem in supervised learning and impedes the predictive performance of classification models. Popular countermeasures include oversampling the minority class. Standard methods like SMOTE rely on finding nearest neighbours and linear interpolations which are problematic in case of high-dimensional, complex data distributions. Generative Adversarial Networks (GANs) have been proposed as an alternative method for generating artificial minority examples as they can model complex distributions. However, prior research on GAN-based oversampling does not incorporate recent advancements from the literature on generating realistic tabular data with GANs. Previous studies also focus on numerical variables whereas categorical features are common in many business applications of classification methods such as credit scoring. The paper propoes an oversampling method based on a conditional Wasserstein GAN that can effectively model tabular datasets with numerical and categorical variables and pays special attention to the down-stream classification task through an auxiliary classifier loss. We benchmark our method against standard oversampling methods and the imbalanced baseline on seven real-world datasets. Empirical results evidence the competitiveness of GAN-based oversampling.
Time series classification (TSC) is home to a number of algorithm groups that utilise different kinds of discriminatory patterns. One of these groups describes classifiers that predict using phase dependant intervals. The time series forest (TSF) classifier is one of the most well known interval methods, and has demonstrated strong performance as well as relative speed in training and predictions. However, recent advances in other approaches have left TSF behind. TSF originally summarises intervals using three simple summary statistics. The `catch22' feature set of 22 time series features was recently proposed to aid time series analysis through a concise set of diverse and informative descriptive characteristics. We propose combining TSF and catch22 to form a new classifier, the Canonical Interval Forest (CIF). We outline additional enhancements to the training procedure, and extend the classifier to include multivariate classification capabilities. We demonstrate a large and significant improvement in accuracy over both TSF and catch22, and show it to be on par with top performers from other algorithmic classes. By upgrading the interval-based component from TSF to CIF, we also demonstrate a significant improvement in the hierarchical vote collective of transformation-based ensembles (HIVE-COTE) that combines different time series representations. HIVE-COTE using CIF is significantly more accurate on the UCR archive than any other classifier we are aware of and represents a new state of the art for TSC.
Discriminating between distributions is an important problem in a number of scientific fields. This motivated the introduction of Linear Optimal Transportation (LOT), which embeds the space of distributions into an $L^2$-space. The transform is defined by computing the optimal transport of each distribution to a fixed reference distribution, and has a number of benefits when it comes to speed of computation and to determining classification boundaries. In this paper, we characterize a number of settings in which LOT embeds families of distributions into a space in which they are linearly separable. This is true in arbitrary dimension, and for families of distributions generated through perturbations of shifts and scalings of a fixed distribution.We also prove conditions under which the $L^2$ distance of the LOT embedding between two distributions in arbitrary dimension is nearly isometric to Wasserstein-2 distance between those distributions. This is of significant computational benefit, as one must only compute $N$ optimal transport maps to define the $N^2$ pairwise distances between $N$ distributions. We demonstrate the benefits of LOT on a number of distribution classification problems.
A key challenge of oversampling in imbalanced classification is that the generation of new minority samples often neglects the usage of majority classes, resulting in most new minority sampling spreading the whole minority space. In view of this, we present a new oversampling framework based on the counterfactual theory. Our framework introduces a counterfactual objective by leveraging the rich inherent information of majority classes and explicitly perturbing majority samples to generate new samples in the territory of minority space. It can be analytically shown that the new minority samples satisfy the minimum inversion, and therefore most of them locate near the decision boundary. Empirical evaluations on benchmark datasets suggest that our approach significantly outperforms the state-of-the-art methods.
Study Objectives: Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts. Methods: A deep neural network model was developed using 15684 polysomnography studies from five different cohorts. We applied four different scenarios: 1) impact of varying time-scales in the model; 2) performance of a single cohort on other cohorts of smaller, greater or equal size relative to the performance of other cohorts on a single cohort; 3) varying the fraction of mixed-cohort training data compared to using single-origin data; and 4) comparing models trained on combinations of data from 2, 3, and 4 cohorts. Results: Overall classification accuracy improved with increasing fractions of training data (0.25$\%$: 0.782 $\pm$ 0.097, 95$\%$ CI [0.777-0.787]; 100$\%$: 0.869 $\pm$ 0.064, 95$\%$ CI [0.864-0.872]), and with increasing number of data sources (2: 0.788 $\pm$ 0.102, 95$\%$ CI [0.787-0.790]; 3: 0.808 $\pm$ 0.092, 95$\%$ CI [0.807-0.810]; 4: 0.821 $\pm$ 0.085, 95$\%$ CI [0.819-0.823]). Different cohorts show varying levels of generalization to other cohorts. Conclusions: Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.
Most emotion recognition methods tackle the emotion understanding task by considering individual emotion independently while ignoring their fuzziness nature and the interconnections among them. In this paper, we explore how emotion correlations can be captured and help different classification tasks. We propose EmoGraph that captures the dependencies among different emotions through graph networks. These graphs are constructed by leveraging the co-occurrence statistics among different emotion categories. Empirical results on two multi-label classification datasets demonstrate that EmoGraph outperforms strong baselines, especially for macro-F1. An additional experiment illustrates the captured emotion correlations can also benefit a single-label classification task.
The detection of anomalies is essential mining task for the security and reliability in computer systems. Logs are a common and major data source for anomaly detection methods in almost every computer system. They collect a range of significant events describing the runtime system status. Recent studies have focused predominantly on one-class deep learning methods on predefined non-learnable numerical log representations. The main limitation is that these models are not able to learn log representations describing the semantic differences between normal and anomaly logs, leading to a poor generalization of unseen logs. We propose Logsy, a classification-based method to learn log representations in a way to distinguish between normal data from the system of interest and anomaly samples from auxiliary log datasets, easily accessible via the internet. The idea behind such an approach to anomaly detection is that the auxiliary dataset is sufficiently informative to enhance the representation of the normal data, yet diverse to regularize against overfitting and improve generalization. We propose an attention-based encoder model with a new hyperspherical loss function. This enables learning compact log representations capturing the intrinsic differences between normal and anomaly logs. Empirically, we show an average improvement of 0.25 in the F1 score, compared to the previous methods. To investigate the properties of Logsy, we perform additional experiments including evaluation of the effect of the auxiliary data size, the influence of expert knowledge, and the quality of the learned log representations. The results show that the learned representation boost the performance of the previous methods such as PCA with a relative improvement of 28.2%.
The incidence of mosquito-borne diseases is significant in under-developed regions, mostly due to the lack of resources to implement aggressive control measurements against mosquito proliferation. A potential strategy to raise community awareness regarding mosquito proliferation is building a live map of mosquito incidences using smartphone apps and crowdsourcing. In this paper, we explore the possibility of identifying Aedes aegypti mosquitoes using machine learning techniques and audio analysis captured from commercially available smartphones. In summary, we downsampled Aedes aegypti wingbeat recordings and used them to train a convolutional neural network (CNN) through supervised learning. As a feature, we used the recording spectrogram to represent the mosquito wingbeat frequency over time visually. We trained and compared three classifiers: a binary, a multiclass, and an ensemble of binary classifiers. In our evaluation, the binary and ensemble models achieved accuracy of 97.65% ($\pm$ 0.55) and 94.56% ($\pm$ 0.77), respectively, whereas the multiclass had an accuracy of 78.12% ($\pm$ 2.09). The best sensitivity was observed in the ensemble approach (96.82% $\pm$ 1.62), followed by the multiclass for the particular case of Aedes aegypti (90.23% $\pm$ 3.83) and the binary (88.49% $\pm$ 6.68). The binary classifier and the multiclass classifier presented the best balance between precision and recall, with F1-measure close to 90%. Although the ensemble classifier achieved the lowest precision, thus impairing its F1-measure (79.95% $\pm$ 2.13), it was the most powerful classifier to detect Aedes aegypti in our dataset.
Inspired by the fruit-fly olfactory circuit, the Fly Bloom Filter [Dasgupta et al., 2018] is able to efficiently summarize the data with a single pass and has been used for novelty detection. We propose a new classifier (for binary and multi-class classification) that effectively encodes the different local neighborhoods for each class with a per-class Fly Bloom Filter. The inference on test data requires an efficient {\tt FlyHash} [Dasgupta, et al., 2017] operation followed by a high-dimensional, but {\em sparse}, dot product with the per-class Bloom Filters. The learning is trivially parallelizable. On the theoretical side, we establish conditions under which the prediction of our proposed classifier on any test example agrees with the prediction of the nearest neighbor classifier with high probability. We extensively evaluate our proposed scheme with over $50$ data sets of varied data dimensionality to demonstrate that the predictive performance of our proposed neuroscience inspired classifier is competitive the the nearest-neighbor classifiers and other single-pass classifiers.