Automatic evaluation of myocardium and pathology plays an important role in the quantitative analysis of patients suffering from myocardial infarction. In this paper, we present a cascaded convolutional neural network framework for myocardial infarction segmentation and classification in delayed-enhancement cardiac MRI. Specifically, we first use a 2D U-Net to segment the whole heart, including the left ventricle and the myocardium. Then, we crop the whole heart as a region of interest (ROI). Finally, a new 2D U-Net is used to segment the infraction and no-reflow areas in the whole heart ROI. The segmentation method can be applied to the classification task where the segmentation results with the infraction or no-reflow areas are classified as pathological cases. Our method took second place in the MICCAI 2020 EMIDEC segmentation task with Dice scores of 86.28%, 62.24%, and 77.76% for myocardium, infraction, and no-reflow areas, respectively, and first place in the classification task with an accuracy of 92%.
Breast cancer is one of the deadliest cancer worldwide. Timely detection could reduce mortality rates. In the clinical routine, classifying benign and malignant tumors from ultrasound (US) imaging is a crucial but challenging task. An automated method, which can deal with the variability of data is therefore needed. In this paper, we compared different Convolutional Neural Networks (CNNs) and transfer learning methods for the task of automated breast tumor classification. The architectures investigated in this study were VGG-16 and Inception V3. Two different training strategies were investigated: the first one was using pretrained models as feature extractors and the second one was to fine-tune the pre-trained models. A total of 947 images were used, 587 corresponded to US images of benign tumors and 360 with malignant tumors. 678 images were used for the training and validation process, while 269 images were used for testing the models. Accuracy and Area Under the receiver operating characteristic Curve (AUC) were used as performance metrics. The best performance was obtained by fine tuning VGG-16, with an accuracy of 0.919 and an AUC of 0.934. The obtained results open the opportunity to further investigation with a view of improving cancer detection.
Gait recognition is a term commonly referred to as an identification problem within the Computer Science field. There are a variety of methods and models capable of identifying an individual based on their pattern of ambulatory locomotion. By surveying the current literature on gait recognition, this paper seeks to identify appropriate metrics, devices, and algorithms for collecting and analyzing data regarding patterns and modes of ambulatory movement across individuals. Furthermore, this survey seeks to motivate interest in a broader scope of longitudinal analysis regarding the perturbations in gait across states (i.e. physiological, emotive, and/or cognitive states). More broadly, inferences to normal versus pathological gait patterns can be attributed, based on both longitudinal and non-longitudinal forms of classification. This may indicate promising research directions and experimental designs, such as creating algorithmic metrics for the quantification of fatigue, or models for forecasting episodic disorders. Furthermore, in conjunction with other measurements of physiological and environmental conditions, pathological gait classification might be applicable to inference for syndromic surveillance of infectious disease states or cognitive impairment.
Identifying events and mapping them to pre-defined event types has long been an important natural language processing problem. Most previous work has been heavily relying on labor-intensive and domain-specific annotations while ignoring the semantic meaning contained in the labels of the event types. As a result, the learned models cannot effectively generalize to new domains, where new event types could be introduced. In this paper, we propose an unsupervised event extraction pipeline, which first identifies events with available tools (e.g., SRL) and then automatically maps them to pre-defined event types with our proposed unsupervised classification model. Rather than relying on annotated data, our model matches the semantics of identified events with those of event type labels. Specifically, we leverage pre-trained language models to contextually represent pre-defined types for both event triggers and arguments. After we map identified events to the target types via representation similarity, we use the event ontology (e.g., argument type "Victim" can only appear as the argument of event type "Attack") as global constraints to regularize the prediction. The proposed approach is shown to be very effective when tested on the ACE-2005 dataset, which has 33 trigger and 22 argument types. Without using any annotation, we successfully map 83% of the triggers and 54% of the arguments to the correct types, almost doubling the performance of previous zero-shot approaches.
For both human readers and pre-trained language models (PrLMs), lexical diversity may lead to confusion and inaccuracy when understanding the underlying semantic meanings of given sentences. By substituting complex words with simple alternatives, lexical simplification (LS) is a recognized method to reduce such lexical diversity, and therefore to improve the understandability of sentences. In this paper, we leverage LS and propose a novel approach which can effectively improve the performance of PrLMs in text classification. A rule-based simplification process is applied to a given sentence. PrLMs are encouraged to predict the real label of the given sentence with auxiliary inputs from the simplified version. Using strong PrLMs (BERT and ELECTRA) as baselines, our approach can still further improve the performance in various text classification tasks.
Feature representation is an important aspect of remote-sensing based image classification. While deep convolutional neural networks are able to effectively amalgamate information, large numbers of parameters often make learned features inscrutable and difficult to transfer to alternative models. In order to better represent statistical texture information for remote-sensing image classification, in this paper, we investigate performing joint dimensionality reduction and classification using a novel histogram neural network. Motivated by a popular dimensionality reduction approach, t-Distributed Stochastic Neighbor Embedding (t-SNE), our proposed method incorporates a classification loss computed on samples in a low-dimensional embedding space. We compare the learned sample embeddings against coordinates found by t-SNE in terms of classification accuracy and qualitative assessment. We also explore use of various divergence measures in the t-SNE objective. The proposed method has several advantages such as readily embedding out-of-sample points and reducing feature dimensionality while retaining class discriminability. Our results show that the proposed approach maintains and/or improves classification performance and reveals characteristics of features produced by neural networks that may be helpful for other applications.
Convolution and pooling are the key operations to learn hierarchical representation for graph classification, where more expressive $k$-order($k>1$) method requires more computation cost, limiting the further applications. In this paper, we investigate the strategy of selecting $k$ via neighborhood information gain and propose light $k$-order convolution and pooling requiring fewer parameters while improving the performance. Comprehensive and fair experiments through six graph classification benchmarks show: 1) the performance improvement is consistent to the $k$-order information gain. 2) the proposed convolution requires fewer parameters while providing competitive results. 3) the proposed pooling outperforms SOTA algorithms in terms of efficiency and performance.
Human motion prediction and understanding is a challenging problem. Due to the complex dynamic of human motion and the non-deterministic aspect of future prediction. We propose a novel sequence-to-sequence model for human motion prediction and feature learning, trained with a modified version of generative adversarial network, with a custom loss function that takes inspiration from human motion animation and can control the variation between multiple predicted motion from the same input poses. Our model learns to predict multiple future sequences of human poses from the same input sequence. We show that the discriminator learns general presentation of human motion by using the learned feature in action recognition task. Furthermore, to quantify the quality of the non-deterministic predictions, we simultaneously train a motion-quality-assessment network that learns the probability that a given sequence of poses is a real human motion or not. We test our model on two of the largest human pose datasets: NTURGB-D and Human3.6M. We train on both single and multiple action types. Its predictive power for motion estimation is demonstrated by generating multiple plausible futures from the same input and show the effect of each of the loss functions. Furthermore, we show that it takes less than half the number of epochs to train an activity recognition network by using the feature learned from the discriminator.
The effect of training data size on machine learning methods has been well investigated over the past two decades. The predictive performance of tree based machine learning methods, in general, improves with a decreasing rate as the size of training data increases. We investigate this in optimal trees ensemble (OTE) where the method fails to learn from some of the training observations due to internal validation. Modified tree selection methods are thus proposed for OTE to cater for the loss of training observations in internal validation. In the first method, corresponding out-of-bag (OOB) observations are used in both individual and collective performance assessment for each tree. Trees are ranked based on their individual performance on the OOB observations. A certain number of top ranked trees is selected and starting from the most accurate tree, subsequent trees are added one by one and their impact is recorded by using the OOB observations left out from the bootstrap sample taken for the tree being added. A tree is selected if it improves predictive accuracy of the ensemble. In the second approach, trees are grown on random subsets, taken without replacement-known as sub-bagging, of the training data instead of bootstrap samples (taken with replacement). The remaining observations from each sample are used in both individual and collective assessments for each corresponding tree similar to the first method. Analysis on 21 benchmark datasets and simulations studies show improved performance of the modified methods in comparison to OTE and other state-of-the-art methods.
Asymmetric binary classification problems, in which the type I and II errors have unequal severity, are ubiquitous in real-world applications. To handle such asymmetry, researchers have developed the cost-sensitive and Neyman-Pearson paradigms for training classifiers to control the more severe type of classification error, say the type I error. The cost-sensitive paradigm is widely used and has straightforward implementations that do not require sample splitting; however, it demands an explicit specification of the costs of the type I and II errors, and an open question is what specification can guarantee a high-probability control on the population type I error. In contrast, the Neyman-Pearson paradigm can train classifiers to achieve a high-probability control of the population type I error, but it relies on sample splitting that reduces the effective training sample size. Since the two paradigms have complementary strengths, it is reasonable to combine their strengths for classifier construction. In this work, we for the first time study the methodological connections between the two paradigms, and we develop the TUBE-CS algorithm to bridge the two paradigms from the perspective of controlling the population type I error.
Remote sensing (RS) scene classification is a challenging task to predict scene categories of RS images. RS images have two main characters: large intra-class variance caused by large resolution variance and confusing information from large geographic covering area. To ease the negative influence from the above two characters. We propose a Multi-granularity Multi-Level Feature Ensemble Network (MGML-FENet) to efficiently tackle RS scene classification task in this paper. Specifically, we propose Multi-granularity Multi-Level Feature Fusion Branch (MGML-FFB) to extract multi-granularity features in different levels of network by channel-separate feature generator (CS-FG). To avoid the interference from confusing information, we propose Multi-granularity Multi-Level Feature Ensemble Module (MGML-FEM) which can provide diverse predictions by full-channel feature generator (FC-FG). Compared to previous methods, our proposed networks have ability to use structure information and abundant fine-grained features. Furthermore, through ensemble learning method, our proposed MGML-FENets can obtain more convincing final predictions. Extensive classification experiments on multiple RS datasets (AID, NWPU-RESISC45, UC-Merced and VGoogle) demonstrate that our proposed networks achieve better performance than previous state-of-the-art (SOTA) networks. The visualization analysis also shows the good interpretability of MGML-FENet.
Semi-supervised learning has been gaining attention as it allows for performing image analysis tasks such as classification with limited labeled data. Some popular algorithms using Generative Adversarial Networks (GANs) for semi-supervised classification share a single architecture for classification and discrimination. However, this may require a model to converge to a separate data distribution for each task, which may reduce overall performance. While progress in semi-supervised learning has been made, less addressed are small-scale, fully-supervised tasks where even unlabeled data is unavailable and unattainable. We therefore, propose a novel GAN model namely External Classifier GAN (EC-GAN), that utilizes GANs and semi-supervised algorithms to improve classification in fully-supervised regimes. Our method leverages a GAN to generate artificial data used to supplement supervised classification. More specifically, we attach an external classifier, hence the name EC-GAN, to the GAN's generator, as opposed to sharing an architecture with the discriminator. Our experiments demonstrate that EC-GAN's performance is comparable to the shared architecture method, far superior to the standard data augmentation and regularization-based approach, and effective on a small, realistic dataset.
In this work, we propose a novel neural network focusing on semantic labeling of ALS point clouds, which investigates the importance of long-range spatial and channel-wise relations and is termed as global relation-aware attentional network (GraNet). GraNet first learns local geometric description and local dependencies using a local spatial discrepancy attention convolution module (LoSDA). In LoSDA, the orientation information, spatial distribution, and elevation differences are fully considered by stacking several local spatial geometric learning modules and the local dependencies are embedded by using an attention pooling module. Then, a global relation-aware attention module (GRA), consisting of a spatial relation-aware attention module (SRA) and a channel relation aware attention module (CRA), are investigated to further learn the global spatial and channel-wise relationship between any spatial positions and feature vectors. The aforementioned two important modules are embedded in the multi-scale network architecture to further consider scale changes in large urban areas. We conducted comprehensive experiments on two ALS point cloud datasets to evaluate the performance of our proposed framework. The results show that our method can achieve higher classification accuracy compared with other commonly used advanced classification methods. The overall accuracy (OA) of our method on the ISPRS benchmark dataset can be improved to 84.5% to classify nine semantic classes, with an average F1 measure (AvgF1) of 73.5%. In detail, we have following F1 values for each object class: powerlines: 66.3%, low vegetation: 82.8%, impervious surface: 91.8%, car: 80.7%, fence: 51.2%, roof: 94.6%, facades: 62.1%, shrub: 49.9%, trees: 82.1%. Besides, experiments were conducted using a new ALS point cloud dataset covering highly dense urban areas.
Power Normalizations (PN) are useful non-linear operators which tackle feature imbalances in classification problems. We study PNs in the deep learning setup via a novel PN layer pooling feature maps. Our layer combines the feature vectors and their respective spatial locations in the feature maps produced by the last convolutional layer of CNN into a positive definite matrix with second-order statistics to which PN operators are applied, forming so-called Second-order Pooling (SOP). As the main goal of this paper is to study Power Normalizations, we investigate the role and meaning of MaxExp and Gamma, two popular PN functions. To this end, we provide probabilistic interpretations of such element-wise operators and discover surrogates with well-behaved derivatives for end-to-end training. Furthermore, we look at the spectral applicability of MaxExp and Gamma by studying Spectral Power Normalizations (SPN). We show that SPN on the autocorrelation/covariance matrix and the Heat Diffusion Process (HDP) on a graph Laplacian matrix are closely related, thus sharing their properties. Such a finding leads us to the culmination of our work, a fast spectral MaxExp which is a variant of HDP for covariances/autocorrelation matrices. We evaluate our ideas on fine-grained recognition, scene recognition, and material classification, as well as in few-shot learning and graph classification.
Classification is an important aspect of hyperspectral images processing and application. At present, the researchers mostly use the classic airborne hyperspectral imagery as the benchmark dataset. However, existing datasets suffer from three bottlenecks: (1) low spatial resolution; (2) low labeled pixels proportion; (3) low degree of subclasses distinction. In this paper, a new benchmark dataset named the Wuhan UAV-borne hyperspectral image (WHU-Hi) dataset was built for hyperspectral image classification. The WHU-Hi dataset with a high spectral resolution (nm level) and a very high spatial resolution (cm level), which we refer to here as H2 imager. Besides, the WHU-Hi dataset has a higher pixel labeling ratio and finer subclasses. Some start-of-art hyperspectral image classification methods benchmarked the WHU-Hi dataset, and the experimental results show that WHU-Hi is a challenging dataset. We hope WHU-Hi dataset can become a strong benchmark to accelerate future research.
In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable features. In particular, we present a novel attention-based spatial contrastive objective to learn locally discriminative and class-agnostic features. As a result, our approach overcomes some of the limitations of the cross-entropy loss, such as its excessive discrimination towards seen classes, which reduces the transferability of features to unseen classes. With extensive experiments, we show that the proposed method outperforms state-of-the-art approaches, confirming the importance of learning good and transferable embeddings for few-shot learning.
Machine Learning applications have brought new insights into a secondary analysis of medical data. Machine Learning helps to develop new drugs, define populations susceptible to certain illnesses, identify predictors of many common diseases. At the same time, Machine Learning results depend on convolution of many factors, including feature selection, class (im)balance, algorithm preference, and performance metrics. In this paper, we present explainable multi-class classification of a large medical data set. We in details discuss knowledge-based feature engineering, data set balancing, best model selection, and parameter tuning. Six algorithms are used in this study: Support Vector Machine (SVM), Na\"ive Bayes, Gradient Boosting, Decision Trees, Random Forest, and Logistic Regression. Our empirical evaluation is done on the UCI Diabetes 130-US hospitals for years 1999-2008 dataset, with the task to classify patient hospital re-admission stay into three classes: 0 days, <30 days, or > 30 days. Our results show that using 23 medication features in learning experiments improves Recall of five out of the six applied learning algorithms. This is a new result that expands the previous studies conducted on the same data. Gradient Boosting and Random Forest outperformed other algorithms in terms of the three-class classification Accuracy.
In our daily life, the scenes around us are always with multiple labels especially in a smart city, i.e., recognizing the information of city operation to response and control. Great efforts have been made by using Deep Neural Networks to recognize multi-label images. Since multi-label image classification is very complicated, people seek to use the attention mechanism to guide the classification process. However, conventional attention-based methods always analyzed images directly and aggressively. It is difficult for them to well understand complicated scenes. In this paper, we propose a global/local attention method that can recognize an image from coarse to fine by mimicking how human-beings observe images. Specifically, our global/local attention method first concentrates on the whole image, and then focuses on local specific objects in the image. We also propose a joint max-margin objective function, which enforces that the minimum score of positive labels should be larger than the maximum score of negative labels horizontally and vertically. This function can further improve our multi-label image classification method. We evaluate the effectiveness of our method on two popular multi-label image datasets (i.e., Pascal VOC and MS-COCO). Our experimental results show that our method outperforms state-of-the-art methods.
Introspection of deep supervised predictive models trained on functional and structural brain imaging may uncover novel markers of Alzheimer's disease (AD). However, supervised training is prone to learning from spurious features (shortcut learning) impairing its value in the discovery process. Deep unsupervised and, recently, contrastive self-supervised approaches, not biased to classification, are better candidates for the task. Their multimodal options specifically offer additional regularization via modality interactions. In this paper, we introduce a way to exhaustively consider multimodal architectures for contrastive self-supervised fusion of fMRI and MRI of AD patients and controls. We show that this multimodal fusion results in representations that improve the results of the downstream classification for both modalities. We investigate the fused self-supervised features projected into the brain space and introduce a numerically stable way to do so.
Choosing a decision threshold is one of the challenging job in any classification tasks. How much the model is accurate, if the deciding boundary is not picked up carefully, its entire performance would go in vain. On the other hand, for imbalance classification where one of the classes is dominant over another, relying on the conventional method of choosing threshold would result in poor performance. Even if the threshold or decision boundary is properly chosen based on machine learning strategies like SVM and decision tree, it will fail at some point for dynamically varying databases and in case of identity-features that are more or less similar, like in face recognition and person re-identification models. Hence, with the need for adaptability of the decision threshold selection for imbalanced classification and incremental database size, an online optimization-based statistical feature learning adaptive technique is developed and tested on the LFW datasets and self-prepared athletes datasets. This method of adopting adaptive threshold resulted in 12-45% improvement in the model accuracy compared to the fixed threshold {0.3,0.5,0.7} that are usually taken via the hit-and-trial method in any classification and identification tasks. Source code for the complete algorithm is available at: https://github.com/Varat7v2/adaptive-threshold