Search

Health mention classification (HMC) involves the classification of an input text as health mention or not. Figurative and non-health mention of disease words makes the classification task challenging. Learning the context of the input text is the key to this problem. The idea is to learn word representation by its surrounding words and utilize emojis in the text to help improve the classification results. In this paper, we improve the word representation of the input text using adversarial training that acts as a regularizer during fine-tuning of the model. We generate adversarial examples by perturbing the word embeddings of the model and then train the model on a pair of clean and adversarial examples. Additionally, we utilize contrastive loss that tries to learn similar representations for the clean example and its perturbed version. We train and evaluate the method on three public datasets. Experiments show that contrastive adversarial training improves the performance significantly in terms of F1-score over the baseline methods of both BERTLarge and RoBERTaLarge on all three datasets. Furthermore, we provide a brief analysis of the results by utilizing the power of explainable AI.

Supervised learning, despite being extremely effective, relies on expensive, time-consuming, and error-prone annotations. Self-supervised learning has recently emerged as a strong alternate to supervised learning in a range of different domains as collecting a large amount of unlabeled data can be achieved by simply crawling the internet. These self-supervised methods automatically discover features relevant to represent an input example by using self-defined proxy tasks. In this paper, we question the potential of commonly employed purely supervised training (starting either from ImageNet pretrained networks or pure random initialization) in contrast to self-supervised representations that can be learned directly using self-supervised representation learning methods on large document image datasets. For this purpose, we leverage a large-scale document image collection (RVL-CDIP) to train ResNet-50 image encoder using two different self-supervision methods (SimCLR and Barlow Twins). Employing a linear classifier on top of self-supervised embeddings from ResNet-50 results in an accuracy of 86.75% as compared to 71.43% from the corresponding ImageNet pretrained embeddings. Similarly, evaluating on Tobacco-3482 dataset using self-supervised embeddings from ResNet-50 yields an accuracy of 88.52% in contrast to 74.16% from the corresponding ImageNet pretrained embeddings. We show that in the case of limited labeled data, this wide gap in performance between self-supervised and fully supervised models persists even after fine-tuning pretrained models. However, a significant reduction in this gap is observed with an increasing amount of data including the case where the model is trained from scratch. Our results show that representations learned using self-supervised representation learning techniques are a viable option for document image classification, specifically in the context of limited labeled data, which is a usual restriction in industrial use cases.

Traditional neural networks trained using point-based maximum likelihood estimation are deterministic models and have exhibited near-human performance in many image classification tasks. However, their insistence on representing network parameters with point-estimates renders them incapable of capturing all possible combinations of the weights; consequently, resulting in a biased predictor towards their initialisation. Most importantly, these deterministic networks are inherently unable to provide any uncertainty estimate for their prediction which is highly sought after in many critical application areas. On the other hand, Bayesian neural networks place a probability distribution on network weights and give a built-in regularisation effect making these models able to learn well from small datasets without overfitting. These networks provide a way of generating posterior distribution which can be used for model's uncertainty estimation. However, Bayesian estimation is computationally very expensive since it greatly widens the parameter space. This paper proposes a hybrid convolutional neural network which combines high accuracy of deterministic models with posterior distribution approximation of Bayesian neural networks. This hybrid architecture is validated on 13 publicly available benchmark classification datasets from a wide range of domains and different modalities like natural scene images, medical images, and time-series. Our results show that the proposed hybrid approach performs better than both deterministic and Bayesian methods in terms of classification accuracy and also provides an estimate of uncertainty for every prediction. We further employ this uncertainty to filter out unconfident predictions and achieve significant additional gain in accuracy for the remaining predictions.

Abstract Background With the advancement of powerful image processing and machine learning techniques, Computer Aided Diagnosis has become ever more prevalent in all fields of medicine including ophthalmology. These methods continue to provide reliable and standardized large scale screening of various image modalities to assist clinicians in identifying diseases. Since optic disc is the most important part of retinal fundus image for glaucoma detection, this paper proposes a two-stage framework that first detects and localizes optic disc and then classifies it into healthy or glaucomatous. Methods The first stage is based on Regions with Convolutional Neural Network (RCNN) and is responsible for localizing and extracting optic disc from a retinal fundus image while the second stage uses Deep Convolutional Neural Network to classify the extracted disc into healthy or glaucomatous. Unfortunately, none of the publicly available retinal fundus image datasets provides any bounding box ground truth required for disc localization. Therefore, in addition to the proposed solution, we also developed a rule-based semi-automatic ground truth generation method that provides necessary annotations for training RCNN based model for automated disc localization. Results The proposed method is evaluated on seven publicly available datasets for disc localization and on ORIGA dataset, which is the largest publicly available dataset with healthy and glaucoma labels, for glaucoma classification. The results of automatic localization mark new state-of-the-art on six datasets with accuracy reaching 100% on four of them. For glaucoma classification we achieved Area Under the Receiver Operating Characteristic Curve equal to 0.874 which is 2.7% relative improvement over the state-of-the-art results previously obtained for classification on ORIGA dataset. Conclusion Once trained on carefully annotated data, Deep Learning based methods for optic disc detection and localization are not only robust, accurate and fully automated but also eliminates the need for dataset-dependent heuristic algorithms. Our empirical evaluation of glaucoma classification on ORIGA reveals that reporting only Area Under the Curve, for datasets with class imbalance and without pre-defined train and test splits, does not portray true picture of the classifier’s performance and calls for additional performance metrics to substantiate the results.

Traditional distance and density-based anomaly detection techniques are unable to detect periodic and seasonality related point anomalies which occur commonly in streaming data, leaving a big gap in time series anomaly detection in the current era of the IoT. To address this problem, we present a novel deep learning-based anomaly detection approach (DeepAnT) for time series data, which is equally applicable to the non-streaming cases. DeepAnT is capable of detecting a wide range of anomalies, i.e., point anomalies, contextual anomalies, and discords in time series data. In contrast to the anomaly detection methods where anomalies are learned, DeepAnT uses unlabeled data to capture and learn the data distribution that is used to forecast the normal behavior of a time series. DeepAnT consists of two modules: time series predictor and anomaly detector. The time series predictor module uses deep convolutional neural network (CNN) to predict the next time stamp on the defined horizon. This module takes a window of time series (used as a context) and attempts to predict the next time stamp. The predicted value is then passed to the anomaly detector module, which is responsible for tagging the corresponding time stamp as normal or abnormal. DeepAnT can be trained even without removing the anomalies from the given data set. Generally, in deep learning-based approaches, a lot of data are required to train a model. Whereas in DeepAnT, a model can be trained on relatively small data set while achieving good generalization capabilities due to the effective parameter sharing of the CNN. As the anomaly detection in DeepAnT is unsupervised, it does not rely on anomaly labels at the time of model generation. Therefore, this approach can be directly applied to real-life scenarios where it is practically impossible to label a big stream of data coming from heterogeneous sensors comprising of both normal as well as anomalous points. We have performed a detailed evaluation of 15 algorithms on 10 anomaly detection benchmarks, which contain a total of 433 real and synthetic time series. Experiments show that DeepAnT outperforms the state-of-the-art anomaly detection methods in most of the cases, while performing on par with others.

This paper presents a novel framework for the demystification of convolutional deep learning models for time-series analysis. This is a step toward making informed/explainable decisions in the domain of time series, powered by deep learning. There have been numerous efforts to increase the interpretability of image-centric deep neural network models, where the learned features are more intuitive to visualize. Visualization in the domain of time series is significantly challenging, as there is no direct interpretation of the filters and inputs compared with the imaging modality. In addition, a little or no concentration has been devoted to the development of such tools in the domain of time series in the past. TSViz provides possibilities to explore and analyze the network from different dimensions at different levels of abstraction, which includes the identification of the parts of the input that were responsible for a particular prediction (including per filter saliency), importance of the different filters present in the network, notion of diversity present in the network through filter clustering, understanding of the main sources of variation learned by the network through inverse optimization, and analysis of the network's robustness against adversarial noise. As a sanity check for the computed influence values, we demonstrate our results on pruning of neural networks based on the computed influence information. These representations allow the user to better understand the network so that the acceptability of these deep models for time-series analysis can be enhanced. This is extremely important in domains, such as finance, industry 4.0, self-driving cars, health care, and counter-terrorism, where reasons for reaching a particular prediction are equally important as the prediction itself. We assess the proposed framework for interpretability with a set of desirable properties essential for any method in this direction.

With the rise in the employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual modalities, time series data has been neglected, with only a handful of methods tested due to their poor intelligibility. We approach the problem of interpretability in a novel way by proposing TSInsight, where we attach an auto-encoder to the classifier with a sparsity-inducing norm on its output and fine-tune it based on the gradients from the classifier and a reconstruction penalty. TSInsight learns to preserve features that are important for prediction by the classifier and suppresses those that are irrelevant, i.e., serves as a feature attribution method to boost the interpretability. In contrast to most other attribution frameworks, TSInsight is capable of generating both instance-based and model-based explanations. We evaluated TSInsight along with nine other commonly used attribution methods on eight different time series datasets to validate its efficacy. The evaluation results show that TSInsight naturally achieves output space contraction; therefore, it is an effective tool for the interpretability of deep time series models.

This paper presents a novel approach for the detection of tables present in documents, leveraging the potential of deep neural networks. Conventional approaches for table detection rely on heuristics that are error prone and specific to a dataset. In contrast, the presented approach harvests the potential of data to recognize tables of arbitrary layout. Most of the prior approaches for table detection are only applicable to PDFs, whereas, the presented approach directly works on images making it generally applicable to any format. The presented approach is based on a novel combination of deformable CNN with faster R-CNN/FPN. Conventional CNN has a fixed receptive field which is problematic for table detection since tables can be present at arbitrary scales along with arbitrary transformations (orientation). Deformable convolution conditions its receptive field on the input itself allowing it to mold its receptive field according to its input. This adaptation of the receptive field enables the network to cater for tables of arbitrary layout. We evaluated the proposed approach on two major publicly available table detection datasets: ICDAR-2013 and ICDAR-2017 POD. The presented approach was able to surpass the state-of-the-art performance on both ICDAR-2013 and ICDAR-2017 POD datasets with a F-measure of 0.994 and 0.968, respectively, indicating its effectiveness and superiority for the task of table detection.

We propose a novel hybrid approach that fuses traditional computer vision techniques with deep learning models to detect figures and formulas from document images. The proposed approach first fuses the different computer vision based image representations, i.e., color transform, connected component analysis, and distance transform, termed as Fi-Fo image representation. The Fi-Fo image representation is then fed to deep models for further refined representation-learning for detecting figures and formulas from document images. The proposed approach is evaluated on a publicly available ICDAR-2017 Page Object Detection (POD) dataset and its corrected version. It produces the state-of-the-art results for formula and figure detection in document images with an f1-score of 0.954 and 0.922, respectively. Ablation study results reveal that the Fi-Fo image representation helps in achieving superior performance in comparison to raw image representation. Results also establish that the hybrid approach helps deep models to learn more discriminating and refined features.

Propensity of skin diseases to manifest in a variety of forms, lack and maldistribution of qualified dermatologists, and exigency of timely and accurate diagnosis call for automated Computer-Aided Diagnosis (CAD). This study aims at extending previous works on CAD for dermatology by exploring the potential of Deep Learning to classify hundreds of skin diseases, improving classification performance, and utilizing disease taxonomy. We trained state-of-the-art Deep Neural Networks on two of the largest publicly available skin image datasets, namely DermNet and ISIC Archive, and also leveraged disease taxonomy, where available, to improve classification performance of these models. On DermNet we establish new state-of-the-art with 80% accuracy and 98% Area Under the Curve (AUC) for classification of 23 diseases. We also set precedence for classifying all 622 unique sub-classes in this dataset and achieved 67% accuracy and 98% AUC. On ISIC Archive we classified all 7 diseases with 93% average accuracy and 99% AUC. This study shows that Deep Learning has great potential to classify a vast array of skin diseases with near-human accuracy and far better reproducibility. It can have a promising role in practical real-time skin disease diagnosis by assisting physicians in large-scale screening using clinical or dermoscopic images.

Following publication of the original article

The need for robust unsupervised anomaly detection in streaming data is increasing rapidly in the current era of smart devices, where enormous data are gathered from numerous sensors. These sensors record the internal state of a machine, the external environment, and the interaction of machines with other machines and humans. It is of prime importance to leverage this information in order to minimize downtime of machines, or even avoid downtime completely by constant monitoring. Since each device generates a different type of streaming data, it is normally the case that a specific kind of anomaly detection technique performs better than the others depending on the data type. For some types of data and use-cases, statistical anomaly detection techniques work better, whereas for others, deep learning-based techniques are preferred. In this paper, we present a novel anomaly detection technique, FuseAD, which takes advantage of both statistical and deep-learning-based approaches by fusing them together in a residual fashion. The obtained results show an increase in area under the curve (AUC) as compared to state-of-the-art anomaly detection methods when FuseAD is tested on a publicly available dataset (Yahoo Webscope benchmark). The obtained results advocate that this fusion-based technique can obtain the best of both worlds by combining their strengths and complementing their weaknesses. We also perform an ablation study to quantify the contribution of the individual components in FuseAD, i.e., the statistical ARIMA model as well as the deep-learning-based convolutional neural network (CNN) model.