As Deep Neural Networks (DNNs) are considered the state-of-the-art in many classification tasks, the question of their semantic generalizations has been raised. To address semantic interpretability of learned features, we introduce a novel idea of classification by re-generation based on variational autoencoder (VAE) in which a separate encoder-decoder pair of VAE is trained for each class. Moreover, the proposed architecture overcomes the scalability issue in current DNN networks as there is no need to re-train the whole network with the addition of new classes and it can be done for each class separately. We also introduce a criterion based on Kullback-Leibler divergence to reject doubtful examples. This rejection criterion should improve the trust in the obtained results and can be further exploited to reject adversarial examples.
We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional distributions. Under these assumptions, we establish an $\Omega(K\log K)$ labeled sample complexity bound without imposing parametric assumptions, where $K$ is the number of classes. Our results suggest that even in nonparametric settings it is possible to learn a near-optimal classifier using only a few labeled samples. Unlike previous theoretical work which focuses on binary classification, we consider general multiclass classification ($K>2$), which requires solving a difficult permutation learning problem. This permutation defines a classifier whose classification error is controlled by the Wasserstein distance between mixing measures, and we provide finite-sample results characterizing the behaviour of the excess risk of this classifier. Finally, we describe three algorithms for computing these estimators based on a connection to bipartite graph matching, and perform experiments to illustrate the superiority of the MLE over the majority vote estimator.
In today's data driven world, storing, processing, and gleaning insights from large-scale data are major challenges. Data compression is often required in order to store large amounts of high-dimensional data, and thus, efficient inference methods for analyzing compressed data are necessary. Building on a recently designed simple framework for classification using binary data, we demonstrate that one can improve classification accuracy of this approach through iterative applications whose output serves as input to the next application. As a side consequence, we show that the original framework can be used as a data preprocessing step to improve the performance of other methods, such as support vector machines. For several simple settings, we showcase the ability to obtain theoretical guarantees for the accuracy of the iterative classification method. The simplicity of the underlying classification framework makes it amenable to theoretical analysis and studying this approach will hopefully serve as a step toward developing theory for more sophisticated deep learning technologies.
In this report, we introduce the outline of our system in Task 3: Disease Classification of ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection. We fine-tuned multiple pre-trained neural network models based on Squeeze-and-Excitation Networks (SENet) which achieved state-of-the-art results in the field of image recognition. In addition, we used the mean teachers as a semi-supervised learning framework and introduced some specially designed data augmentation strategies for skin lesion analysis. We confirmed our data augmentation strategy improved classification performance and demonstrated 87.2% in balanced accuracy on the official ISIC2018 validation dataset.
Efficient and easy segmentation of images and volumes is of great practical importance. Segmentation problems that motivate our approach originate from microscopy imaging commonly used in materials science, medicine, and biology. We formulate image segmentation as a probabilistic pixel classification problem, and we apply segmentation as a step towards characterising image content. Our method allows the user to define structures of interest by interactively marking a subset of pixels. Thanks to the real-time feedback, the user can place new markings strategically, depending on the current outcome. The final pixel classification may be obtained from a very modest user input. An important ingredient of our method is a graph that encodes image content. This graph is built in an unsupervised manner during initialisation and is based on clustering of image features. Since we combine a limited amount of user-labelled data with the clustering information obtained from the unlabelled parts of the image, our method fits in the general framework of semi-supervised learning. We demonstrate how this can be a very efficient approach to segmentation through pixel classification.
Neural networks achieve the state-of-the-art in image classification tasks. However, they can encode spurious variations or biases that may be present in the training data. For example, training an age predictor on a dataset that is not balanced for gender can lead to gender biased predicitons (e.g. wrongly predicting that males are older if only elderly males are in the training set). We present two distinct contributions: 1) An algorithm that can remove multiple sources of variation from the feature representation of a network. We demonstrate that this algorithm can be used to remove biases from the feature representation, and thereby improve classification accuracies, when training networks on extremely biased datasets. 2) An ancestral origin database of 14,000 images of individuals from East Asia, the Indian subcontinent, sub-Saharan Africa, and Western Europe. We demonstrate on this dataset, for a number of facial attribute classification tasks, that we are able to remove racial biases from the network feature representation.
A conceptually simple way to classify images is to directly compare test-set data and training-set data. The accuracy of this approach is limited by the method of comparison used, and by the extent to which the training-set data cover configuration space. Here we show that this coverage can be substantially increased using coarse graining (replacing groups of images by their centroids) and stochastic sampling (using distinct sets of centroids in combination). We use the MNIST and Fashion-MNIST data sets to show that a principled coarse-graining algorithm can convert training images into fewer image centroids without loss of accuracy of classification of test-set images by nearest-neighbor classification. Distinct batches of centroids can be used in combination as a means of stochastically sampling configuration space, and can classify test-set data more accurately than can the unaltered training set. On the MNIST and Fashion-MNIST data sets this approach converts nearest-neighbor classification from a mid-ranking- to an upper-ranking member of the set of classical machine-learning techniques.
Generally, facial age variations affect gender classification accuracy significantly, because facial shape and skin texture change as they grow old. This requires re-examination on the gender classification system to consider facial age information. In this paper, we propose Multi-expert Gender Classification on Age Group (MGA), an end-to-end multi-task learning schemes of age estimation and gender classification. First, two types of deep neural networks are utilized; Convolutional Appearance Network (CAN) for facial appearance feature and Deep Geometry Network (DGN) for facial geometric feature. Then, CAN and DGN are integrated by the proposed model integration strategy and fine-tuned in order to improve age and gender classification accuracy. The facial images are categorized into one of three age groups (young, adult and elder group) based on their estimated age, and the system makes a gender prediction according to average fusion strategy of three gender classification experts, which are trained to fit gender characteristics of each age group. Rigorous experimental results conducted on the challenging databases suggest that the proposed MGA outperforms several state-of-art researches with smaller computational cost.
Adversarial Reprogramming has demonstrated success in utilizing pre-trained neural network classifiers for alternative classification tasks without modification to the original network. An adversary in such an attack scenario trains an additive contribution to the inputs to repurpose the neural network for the new classification task. While this reprogramming approach works for neural networks with a continuous input space such as that of images, it is not directly applicable to neural networks trained for tasks such as text classification, where the input space is discrete. Repurposing such classification networks would require the attacker to learn an adversarial program that maps inputs from one discrete space to the other. In this work, we introduce a context-based vocabulary remapping model to reprogram neural networks trained on a specific sequence classification task, for a new sequence classification task desired by the adversary. We propose training procedures for this adversarial program in both white-box and black-box settings. We demonstrate the application of our model by adversarially repurposing various text-classification models including LSTM, bi-directional LSTM and CNN for alternate classification tasks.
Noise Contrastive Estimation (NCE) is a powerful parameter estimation method for log-linear models, which avoids calculation of the partition function or its derivatives at each training step, a computationally demanding step in many cases. It is closely related to negative sampling methods, now widely used in NLP. This paper considers NCE-based estimation of conditional models. Conditional models are frequently encountered in practice; however there has not been a rigorous theoretical analysis of NCE in this setting, and we will argue there are subtle but important questions when generalizing NCE to the conditional case. In particular, we analyze two variants of NCE for conditional models: one based on a classification objective, the other based on a ranking objective. We show that the ranking-based variant of NCE gives consistent parameter estimates under weaker assumptions than the classification-based method; we analyze the statistical efficiency of the ranking-based and classification-based variants of NCE; finally we describe experiments on synthetic data and language modeling showing the effectiveness and trade-offs of both methods.
Efficient distributed numerical word representation models (word embeddings) combined with modern machine learning algorithms have recently yielded considerable improvement on automatic document classification tasks. However, the effectiveness of such techniques has not been assessed for the hierarchical text classification (HTC) yet. This study investigates the application of those models and algorithms on this specific problem by means of experimentation and analysis. We trained classification models with prominent machine learning algorithm implementations---fastText, XGBoost, SVM, and Keras' CNN---and noticeable word embeddings generation methods---GloVe, word2vec, and fastText---with publicly available data and evaluated them with measures specifically appropriate for the hierarchical context. FastText achieved an ${}_{LCA}F_1$ of 0.893 on a single-labeled version of the RCV1 dataset. An analysis indicates that using word embeddings and its flavors is a very promising approach for HTC.
This paper studies the problems of vehicle make & model classification. Some of the main challenges are reaching high classification accuracy and reducing the annotation time of the images. To address these problems, we have created a fine-grained database using online vehicle marketplaces of Turkey. A pipeline is proposed to combine an SSD (Single Shot Multibox Detector) model with a CNN (Convolutional Neural Network) model to train on the database. In the pipeline, we first detect the vehicles by following an algorithm which reduces the time for annotation. Then, we feed them into the CNN model. It is reached approximately 4% better classification accuracy result than using a conventional CNN model. Next, we propose to use the detected vehicles as ground truth bounding box (GTBB) of the images and feed them into an SSD model in another pipeline. At this stage, it is reached reasonable classification accuracy result without using perfectly shaped GTBB. Lastly, an application is implemented in a use case by using our proposed pipelines. It detects the unauthorized vehicles by comparing their license plate numbers and make & models. It is assumed that license plates are readable.
Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification models suffer from the lack of training data in many real-world applications. Although many semi-supervised and weakly-supervised text classification models exist, they cannot be easily applied to deep neural models and meanwhile support limited supervision types. In this paper, we propose a weakly-supervised method that addresses the lack of training data in neural text classification. Our method consists of two modules: (1) a pseudo-document generator that leverages seed information to generate pseudo-labeled documents for model pre-training, and (2) a self-training module that bootstraps on real unlabeled data for model refinement. Our method has the flexibility to handle different types of weak supervision and can be easily integrated into existing deep neural models for text classification. We have performed extensive experiments on three real-world datasets from different domains. The results demonstrate that our proposed method achieves inspiring performance without requiring excessive training data and outperforms baseline methods significantly.
In the sentence classification task, context formed from sentences adjacent to the sentence being classified can provide important information for classification. This context is, however, often ignored. Where methods do make use of context, only small amounts are considered, making it difficult to scale. We present a new method for sentence classification, Context-LSTM-CNN, that makes use of potentially large contexts. The method also utilizes long-range dependencies within the sentence being classified, using an LSTM, and short-span features, using a stacked CNN. Our experiments demonstrate that this approach consistently improves over previous methods on two different datasets.
We present a machine learning based method for noise classification using a low-power and inexpensive IoT unit. We use Mel-frequency cepstral coefficients for audio feature extraction and supervised classification algorithms (that is, support vector machine and k-nearest neighbors) for noise classification. We evaluate our approach experimentally with a dataset of about 3000 sound samples grouped in eight sound classes (such as, car horn, jackhammer, or street music). We explore the parameter space of support vector machine and k-nearest neighbors algorithms to estimate the optimal parameter values for classification of sound samples in the dataset under study. We achieve a noise classification accuracy in the range 85% -- 100%. Training and testing of our k-nearest neighbors (k = 1) implementation on Raspberry Pi Zero W is less than a second for a dataset with features of more than 3000 sound samples.
Processing and analyzing of massive clinical data are resource intensive and time consuming with traditional analytic tools. Electroencephalogram (EEG) is one of the major technologies in detecting and diagnosing various brain disorders, and produces huge volume big data to process. In this study, we propose a big data framework to diagnose sleep disorders by classifying the sleep stages from EEG signals. The framework is developed with open source SparkMlib Libraries. We also tested and evaluated the proposed framework by measuring the scalabilities of well-known classification algorithms on physionet sleep records.
Existing work on automated hate speech detection typically focuses on binary classification or on differentiating among a small set of categories. In this paper, we propose a novel method on a fine-grained hate speech classification task, which focuses on differentiating among 40 hate groups of 13 different hate group categories. We first explore the Conditional Variational Autoencoder (CVAE) as a discriminative model and then extend it to a hierarchical architecture to utilize the additional hate category information for more accurate prediction. Experimentally, we show that incorporating the hate category information for training can significantly improve the classification performance and our proposed model outperforms commonly-used discriminative models.
We evaluated the effectiveness of an automated bird sound identification system in a situation that emulates a realistic, typical application. We trained classification algorithms on a crowd-sourced collection of bird audio recording data and restricted our training methods to be completely free of manual intervention. The approach is hence directly applicable to the analysis of multiple species collections, with labelling provided by crowd-sourced collection. We evaluated the performance of the bird sound recognition system on a realistic number of candidate classes, corresponding to real conditions. We investigated the use of two canonical classification methods, chosen due to their widespread use and ease of interpretation, namely a k Nearest Neighbour (kNN) classifier with histogram-based features and a Support Vector Machine (SVM) with time-summarisation features. We further investigated the use of a certainty measure, derived from the output probabilities of the classifiers, to enhance the interpretability and reliability of the class decisions. Our results demonstrate that both identification methods achieved similar performance, but we argue that the use of the kNN classifier offers somewhat more flexibility. Furthermore, we show that employing an outcome certainty measure provides a valuable and consistent indicator of the reliability of classification results. Our use of generic training data and our investigation of probabilistic classification methodologies that can flexibly address the variable number of candidate species/classes that are expected to be encountered in the field, directly contribute to the development of a practical bird sound identification system with potentially global application. Further, we show that certainty measures associated with identification outcomes can significantly contribute to the practical usability of the overall system.
Consider a query-based data acquisition problem that aims to recover the values of $k$ binary variables from parity (XOR) measurements of chosen subsets of the variables. Assume the response model where only a randomly selected subset of the measurements is received. We propose a method for designing a sequence of queries so that the variables can be identified with high probability using as few ($n$) measurements as possible. We define the query difficulty $\bar{d}$ as the average size of the query subsets and the sample complexity $n$ as the minimum number of measurements required to attain a given recovery accuracy. We obtain fundamental trade-offs between recovery accuracy, query difficulty, and sample complexity. In particular, the necessary and sufficient sample complexity required for recovering all $k$ variables with high probability is $n = c_0 \max\{k, (k \log k)/\bar{d}\}$ and the sample complexity for recovering a fixed proportion $(1-\delta)k$ of the variables for $\delta=o(1)$ is $n = c_1\max\{k, (k \log(1/\delta))/\bar{d}\}$, where $c_0, c_1>0$.
Distant supervision is a popular method for performing relation extraction from text that is known to produce noisy labels. Most progress in relation extraction and classification has been made with crowdsourced corrections to distant-supervised labels, and there is evidence that indicates still more would be better. In this paper, we explore the problem of propagating human annotation signals gathered for open-domain relation classification through the CrowdTruth methodology for crowdsourcing, that captures ambiguity in annotations by measuring inter-annotator disagreement. Our approach propagates annotations to sentences that are similar in a low dimensional embedding space, expanding the number of labels by two orders of magnitude. Our experiments show significant improvement in a sentence-level multi-class relation classifier.