Using attention weights to identify information that is important for models' decision-making is a popular approach to interpret attention-based neural networks. This is commonly realized in practice through the generation of a heat-map for every single document based on attention weights. However, this interpretation method is fragile, and easy to find contradictory examples. In this paper, we propose a corpus-level explanation approach, which aims to capture causal relationships between keywords and model predictions via learning the importance of keywords for predicted labels across a training corpus based on attention weights. Based on this idea, we further propose a concept-based explanation method that can automatically learn higher-level concepts and their importance to model prediction tasks. Our concept-based explanation method is built upon a novel Abstraction-Aggregation Network, which can automatically cluster important keywords during an end-to-end training process. We apply these methods to the document classification task and show that they are powerful in extracting semantically meaningful keywords and concepts. Our consistency analysis results based on an attention-based Na\"ive Bayes classifier also demonstrate these keywords and concepts are important for model predictions.
Traditionally, deep convolutional neural networks consist of a series of convolutional and pooling layers followed by one or more fully connected (FC) layers to perform the final classification. While this design has been successful, for datasets with a large number of categories, the fully connected layers often account for a large percentage of the network's parameters. For applications with memory constraints, such as mobile devices and embedded platforms, this is not ideal. Recently, a family of architectures that involve replacing the learned fully connected output layer with a fixed layer has been proposed as a way to achieve better efficiency. In this paper we examine this idea further and demonstrate that fixed classifiers offer no additional benefit compared to simply removing the output layer along with its parameters. We further demonstrate that the typical approach of having a fully connected final output layer is inefficient in terms of parameter count. We are able to achieve comparable performance to a traditionally learned fully connected classification output layer on the ImageNet-1K, CIFAR-100, Stanford Cars-196, and Oxford Flowers-102 datasets, while not having a fully connected output layer at all.
The representations of the Earth's surface vary from one geographic region to another. For instance, the appearance of urban areas differs between continents, and seasonality influences the appearance of vegetation. To capture the diversity within a single category, like as urban or vegetation, requires a large model capacity and, consequently, large datasets. In this work, we propose a different perspective and view this diversity as an inductive transfer learning problem where few data samples from one region allow a model to adapt to an unseen region. We evaluate the model-agnostic meta-learning (MAML) algorithm on classification and segmentation tasks using globally and regionally distributed datasets. We find that few-shot model adaptation outperforms pre-training with regular gradient descent and fine-tuning on (1) the Sen12MS dataset and (2) DeepGlobe data when the source domain and target domain differ. This indicates that model optimization with meta-learning may benefit tasks in the Earth sciences whose data show a high degree of diversity from region to region, while traditional gradient-based supervised learning remains suitable in the absence of a feature or label shift.
Autism spectrum disorder (ASD) affects the brain connectivity at different levels. Nonetheless, non-invasively distinguishing such effects using magnetic resonance imaging (MRI) remains very challenging to machine learning diagnostic frameworks due to ASD heterogeneity. So far, existing network neuroscience works mainly focused on functional (derived from functional MRI) and structural (derived from diffusion MRI) brain connectivity, which might not capture relational morphological changes between brain regions. Indeed, machine learning (ML) studies for ASD diagnosis using morphological brain networks derived from conventional T1-weighted MRI are very scarce. To fill this gap, we leverage crowdsourcing by organizing a Kaggle competition to build a pool of machine learning pipelines for neurological disorder diagnosis with application to ASD diagnosis using cortical morphological networks derived from T1-weighted MRI. During the competition, participants were provided with a training dataset and only allowed to check their performance on a public test data. The final evaluation was performed on both public and hidden test datasets based on accuracy, sensitivity, and specificity metrics. Teams were ranked using each performance metric separately and the final ranking was determined based on the mean of all rankings. The first-ranked team achieved 70% accuracy, 72.5% sensitivity, and 67.5% specificity, while the second-ranked team achieved 63.8%, 62.5%, 65% respectively. Leveraging participants to design ML diagnostic methods within a competitive machine learning setting has allowed the exploration and benchmarking of wide spectrum of ML methods for ASD diagnosis using cortical morphological networks.
Automated pavement distress detection via road images is still a challenging issue among pavement researchers and computer-vision community. In recent years, advancement in deep learning has enabled researchers to develop robust tools for analyzing pavement images at unprecedented accuracies. Nevertheless, deep learning models necessitate a big ground truth dataset, which is often not readily accessible for pavement field. In this study, we reviewed our previous study, which a labeled pavement dataset was presented as the first step towards a more robust, easy-to-deploy pavement condition assessment system. In total, 7237 google street-view images were extracted, manually annotated for classification (nine categories of distress classes). Afterward, YOLO (you look only once) deep learning framework was implemented to train the model using the labeled dataset. In the current study, a U-net based model is developed to quantify the severity of the distresses, and finally, a hybrid model is developed by integrating the YOLO and U-net model to classify the distresses and quantify their severity simultaneously. Various pavement condition indices are developed by implementing various machine learning algorithms using the YOLO deep learning framework for distress classification and U-net for segmentation and distress densification. The output of the distress classification and segmentation models are used to develop a comprehensive pavement condition tool which rates each pavement image according to the type and severity of distress extracted.
In the current research of neural networks, the activation function is manually specified by human and not able to change themselves during training. This paper focus on how to make the activation function trainable for deep neural networks. We use series and linear combination of different activation functions make activation functions continuously variable. Also, we test the performance of CNNs with Fourier series simulated activation(Fourier-CNN) and CNNs with linear combined activation function (LC-CNN) on Cifar-10 dataset. The result shows our trainable activation function reveals better performance than the most used ReLU activation function. Finally, we improves the performance of Fourier-CNN with Autoencoder, and test the performance of PSO algorithm in optimizing the parameters of networks
Learning continuous representations from unlabeled textual data has been increasingly studied for benefiting semi-supervised learning. Although it is relatively easier to interpret discrete representations, due to the difficulty of training, learning discrete representations for unlabeled textual data has not been widely explored. This work proposes TIGAN that learns to encode texts into two disentangled representations, including a discrete code and a continuous noise, where the discrete code represents interpretable topics, and the noise controls the variance within the topics. The discrete code learned by TIGAN can be used for unsupervised text classification. Compared to other unsupervised baselines, the proposed TIGAN achieves superior performance on six different corpora. Also, the performance is on par with a recently proposed weakly-supervised text classification method. The extracted topical words for representing latent topics show that TIGAN learns coherent and highly interpretable topics.
We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to decisions produced by classification models. They can be applied with black-box models and models that can be specified as logic programs, such as rule-based classifiers. The main focus in on the specification and computation of maximum responsibility causal explanations. The use of additional semantic knowledge is investigated.
Deep learning based methods have achieved impressive results in many applications for image-based diet assessment such as food classification and food portion size estimation. However, existing methods only focus on one task at a time, making it difficult to apply in real life when multiple tasks need to be processed together. In this work, we propose an end-to-end multi-task framework that can achieve both food classification and food portion size estimation. We introduce a food image dataset collected from a nutrition study where the groundtruth food portion is provided by registered dietitians. The multi-task learning uses L2-norm based soft parameter sharing to train the classification and regression tasks simultaneously. We also propose the use of cross-domain feature adaptation together with normalization to further improve the performance of food portion size estimation. Our results outperforms the baseline methods for both classification accuracy and mean absolute error for portion estimation, which shows great potential for advancing the field of image-based dietary assessment.
OVID-19 is a world-wide disease that has been declared as a pandemic by the World Health Organization. Computer Tomography (CT) imaging of the chest seems to be a valid diagnosis tool to detect COVID-19 promptly and to control the spread of the disease. Deep Learning has been extensively used in medical imaging and convolutional neural networks (CNNs) have been also used for classification of CT images. We propose a light CNN design based on the model of the SqueezeNet, for the efficient discrimination of COVID-19 CT images with other CT images (community-acquired pneumonia and/or healthy images). On the tested datasets, the proposed modified SqueezeNet CNN achieved 83.00\% of accuracy, 85.00\% of sensitivity, 81.00\% of specificity, 81.73\% of precision and 0.8333 of F1Score in a very efficient way (7.81 seconds medium-end laptot without GPU acceleration). Besides performance, the average classification time is very competitive with respect to more complex CNN designs, thus allowing its usability also on medium power computers. In the next future we aim at improving the performances of the method along two directions: 1) by increasing the training dataset (as soon as other CT images will be available); 2) by introducing an efficient pre-processing strategy.
Efficient inspection and accurate diagnosis are required for civil infrastructures with 50 years since completion. Especially in municipalities, the shortage of technical staff and budget constraints on repair expenses have become a critical problem. If we can detect damaged photos automatically per-pixels from the record of the inspection record in addition to the 5-step judgment and countermeasure classification of eye-inspection vision, then it is possible that countermeasure information can be provided more flexibly, whether we need to repair and how large the expose of damage interest. A piece of damage photo is often sparse as long as it is not zoomed around damage, exactly the range where the detection target is photographed, is at most only 1%. Generally speaking, rebar exposure is frequently occurred, and there are many opportunities to judge repair measure. In this paper, we propose three damage detection methods of transfer learning which enables semantic segmentation in an image with low pixels using damaged photos of human eye-inspection. Also, we tried to create a deep convolutional network from scratch with the preprocessing that random crops with rotations are generated. In fact, we show the results applied this method using the 208 rebar exposed images on the 106 real-world bridges. Finally, future tasks of damage detection modeling are mentioned.
We introduce a comprehensive screening platform for the COVID-19 (a.k.a., SARS-CoV-2) pneumonia. The proposed AI-based system works on chest x-ray (CXR) images to predict whether a patient is infected with the COVID-19 disease. Although the recent international joint effort on making the availability of all sorts of open data, the public collection of CXR images is still relatively small for reliably training a deep neural network (DNN) to carry out COVID-19 prediction. To better address such inefficiency, we design a cascaded learning strategy to improve both the sensitivity and the specificity of the resulting DNN classification model. Our approach leverages a large CXR image dataset of non-COVID-19 pneumonia to generalize the original well-trained classification model via a cascaded learning scheme. The resulting screening system is shown to achieve good classification performance on the expanded dataset, including those newly added COVID-19 CXR images.
Convolutional neural networks (CNNs) have achieved the state-of-the-art performance in skin lesion analysis. Compared with single CNN classifier, combining the results of multiple classifiers via fusion approaches shows to be more effective and robust. Since the skin lesion datasets are usually limited and statistically biased, while designing an effective fusion approach, it is important to consider not only the performance of each classifier on the training/validation dataset, but also the relative discriminative power (e.g., confidence) of each classifier regarding an individual sample in the testing phase, which calls for an active fusion approach. Furthermore, in skin lesion analysis, the data of certain classes (e.g., the benign lesions) is usually abundant making them an over-represented majority, while the data of some other classes (e.g., the cancerous lesions) is deficient, making them an underrepresented minority. It is more crucial to precisely identify the samples from an underrepresented (i.e., in terms of the amount of data) but more important minority class (e.g., certain cancerous lesion). In other words, misclassifying a more severe lesion to a benign or less severe lesion should have relative more cost (e.g., money, time and even lives). To address such challenges, we present CS-AF, a cost-sensitive multi-classifier active fusion framework for skin lesion classification. In the experimental evaluation, we prepared 96 base classifiers (of 12 CNN architectures) on the ISIC research datasets. Our experimental results show that our framework consistently outperforms the static fusion competitors.
We investigate and demonstrate the use of convolutional neural networks (CNNs) for the task of distinguishing between merging and non-merging galaxies in simulated images, and for the first time at high redshifts (i.e. $z=2$). We extract images of merging and non-merging galaxies from the Illustris-1 cosmological simulation and apply observational and experimental noise that mimics that from the Hubble Space Telescope; the data without noise form a "pristine" data set and that with noise form a "noisy" data set. The test set classification accuracy of the CNN is $79\%$ for pristine and $76\%$ for noisy. The CNN outperforms a Random Forest classifier, which was shown to be superior to conventional one- or two-dimensional statistical methods (Concentration, Asymmetry, the Gini, $M_{20}$ statistics etc.), which are commonly used when classifying merging galaxies. We also investigate the selection effects of the classifier with respect to merger state and star formation rate, finding no bias. Finally, we extract Grad-CAMs (Gradient-weighted Class Activation Mapping) from the results to further assess and interrogate the fidelity of the classification model.
Aggressive driving (i.e., car drifting) is a dangerous behavior that puts human safety and life into a significant risk. This behavior is considered as an anomaly concerning the regular traffic in public transportation roads. Recent techniques in deep learning proposed new approaches for anomaly detection in different contexts such as pedestrian monitoring, street fighting, and threat detection. In this paper, we propose a new anomaly detection framework applied to the detection of aggressive driving behavior. Our contribution consists in the development of a 3D neural network architecture, based on the state-of-the-art EfficientNet 2D image classifier, for the aggressive driving detection in videos. We propose an EfficientNet3D CNN feature extractor for video analysis, and we compare it with existing feature extractors. We also created a dataset of car drifting in Saudi Arabian context https://www.youtube.com/watch?v=vLzgye1-d1k . To the best of our knowledge, this is the first work that addresses the problem of aggressive driving behavior using deep learning.
Apple orchards in the U.S. are under constant threat from a large number of pathogens and insects. Appropriate and timely deployment of disease management depends on early disease detection. Incorrect and delayed diagnosis can result in either excessive or inadequate use of chemicals, with increased production costs, environmental, and health impacts. We have manually captured 3,651 high-quality, real-life symptom images of multiple apple foliar diseases, with variable illumination, angles, surfaces, and noise. A subset, expert-annotated to create a pilot dataset for apple scab, cedar apple rust, and healthy leaves, was made available to the Kaggle community for 'Plant Pathology Challenge'; part of the Fine-Grained Visual Categorization (FGVC) workshop at CVPR 2020 (Computer Vision and Pattern Recognition). We also trained an off-the-shelf convolutional neural network (CNN) on this data for disease classification and achieved 97% accuracy on a held-out test set. This dataset will contribute towards development and deployment of machine learning-based automated plant disease classification algorithms to ultimately realize fast and accurate disease detection. We will continue to add images to the pilot dataset for a larger, more comprehensive expert-annotated dataset for future Kaggle competitions and to explore more advanced methods for disease classification and quantification.
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs). While such a practice has been studied as a way to leverage privileged information about the distribution of the data, a well-trained learner with soft classification outputs should be first obtained as a prior to generate such privileged information. To solve such chicken-egg problem, we propose COLAM framework that Co-Learns DNNs and soft labels through Alternating Minimization of two objectives - (a) the training loss subject to soft labels and (b) the objective to learn improved soft labels - in one end-to-end training procedure. We performed extensive experiments to compare our proposed method with a series of baselines. The experiment results show that COLAM achieves improved performance on many tasks with better testing classification accuracy. We also provide both qualitative and quantitative analyses that explain why COLAM works well.
Sentiment classification is a fundamental task in content analysis. Although deep learning has demonstrated promising performance in text classification compared with shallow models, it is still not able to train a satisfying classifier for text sentiment. Human beings are more sophisticated than machine learning models in terms of understanding and capturing the emotional polarities of texts. In this paper, we leverage the power of human intelligence into text sentiment classification. We propose Crowd-based neural networks for Text Sentiment Classification (CrowdTSC for short). We design and post the questions on a crowdsourcing platform to collect the keywords in texts. Sampling and clustering are utilized to reduce the cost of crowdsourcing. Also, we present an attention-based neural network and a hybrid neural network, which incorporate the collected keywords as human being's guidance into deep neural networks. Extensive experiments on public datasets confirm that CrowdTSC outperforms state-of-the-art models, justifying the effectiveness of crowd-based keyword guidance.
Because hyperspectral remote sensing images contain a lot of redundant information and the data structure is highly non-linear, leading to low classification accuracy of traditional machine learning methods. The latest research shows that hyperspectral image classification based on deep convolutional neural network has high accuracy. However, when a small amount of data is used for training, the classification accuracy of deep learning methods is greatly reduced. In order to solve the problem of low classification accuracy of existing algorithms on small samples of hyperspectral images, a multi-scale residual network is proposed. The multi-scale extraction and fusion of spatial and spectral features is realized by adding a branch structure into the residual block and using convolution kernels of different sizes in the branch. The spatial and spectral information contained in hyperspectral images are fully utilized to improve the classification accuracy. In addition, in order to improve the speed and prevent overfitting, the model uses dynamic learning rate, BN and Dropout strategies. The experimental results show that the overall classification accuracy of this method is 99.07% and 99.96% respectively in the data set of Indian Pines and Pavia University, which is better than other algorithms.
Transfer learning and joint learning approaches are extensively used to improve the performance of Convolutional Neural Networks (CNNs). In medical imaging applications in which the target dataset is typically very small, transfer learning improves feature learning while joint learning has shown effectiveness in improving the network's generalization and robustness. In this work, we study the combination of these two approaches for the problem of liver lesion segmentation and classification. For this purpose, 332 abdominal CT slices containing lesion segmentation and classification of three lesion types are evaluated. For feature learning, the dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge is used. Joint learning shows improvement in both segmentation and classification results. We show that a simple joint framework outperforms the commonly used multi-task architecture (Y-Net), achieving an improvement of 10% in classification accuracy, compared to a 3% improvement with Y-Net.