Deep learning can promote the mammography-based computer-aided diagnosis (CAD) for breast cancers, but it generally suffers from the small sample size problem. Self-supervised learning (SSL) has shown its effectiveness in medical image analysis with limited training samples. However, the network model sometimes cannot be well pre-trained in the conventional SSL framework due to the limitation of the pretext task and fine-tuning mechanism. In this work, a Task-driven Self-supervised Bi-channel Networks (TSBN) framework is proposed to improve the performance of classification model the mammography-based CAD. In particular, a new gray-scale image mapping (GSIM) is designed as the pretext task, which embeds the class label information of mammograms into the image restoration task to improve discriminative feature representation. The proposed TSBN then innovatively integrates different network architecture, including the image restoration network and the classification network, into a unified SSL framework. It jointly trains the bi-channel network models and collaboratively transfers the knowledge from the pretext task network to the downstream task network with improved diagnostic accuracy. The proposed TSBN is evaluated on a public INbreast mammogram dataset. The experimental results indicate that it outperforms the conventional SSL and multi-task learning algorithms for diagnosis of breast cancers with limited samples.
Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data make accurate classification challenging for traditional methods. In the last few years, Deep Learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies on the said topic. Primarily, we will encapsulate the main challenges of traditional machine learning for HSIC and then we will acquaint the superiority of DL to address these problems. This survey breakdown the state-of-the-art DL frameworks into spectral features, spatial features, and together spatial-spectral features to systematically analyze the achievements (future research directions as well) of these frameworks for HSIC. Moreover, we will consider the fact that DL requires a large number of labeled training examples whereas acquiring such a number for HSIC is challenging in terms of time and cost. Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines.
Neural networks are prone to learning shortcuts -- they often model simple correlations, ignoring more complex ones that potentially generalize better. Prior works on image classification show that instead of learning a connection to object shape, deep classifiers tend to exploit spurious correlations with low-level texture or the background for solving the classification task. In this work, we take a step towards more robust and interpretable classifiers that explicitly expose the task's causal structure. Building on current advances in deep generative modeling, we propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision. By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background; hence, they allow for generating counterfactual images. We demonstrate the ability of our model to generate such images on MNIST and ImageNet. Further, we show that the counterfactual images can improve out-of-distribution robustness with a marginal drop in performance on the original classification task, despite being synthetic. Lastly, our generative model can be trained efficiently on a single GPU, exploiting common pre-trained models as inductive biases.
As the reach of the internet increases, pejorative terms started flooding over social media platforms. This leads to the necessity of identifying hostile content on social media platforms. Identification of hostile contents on low-resource languages like Hindi poses different challenges due to its diverse syntactic structure compared to English. In this paper, we develop a simple ensemble based model on pre-trained mBERT and popular classification algorithms like Artificial Neural Network (ANN) and XGBoost for hostility detection in Hindi posts. We formulated this problem as binary classification (hostile and non-hostile class) and multi-label multi-class classification problem (for more fine-grained hostile classes). We received third overall rank in the competition and weighted F1-scores of ~0.969 and ~0.61 on the binary and multi-label multi-class classification tasks respectively.
Recommending appropriate algorithms to a classification problem is one of the most challenging issues in the field of data mining. The existing algorithm recommendation models are generally constructed on only one kind of meta-features by single learners. Considering that i) ensemble learners usually show better performance and ii) different kinds of meta-features characterize the classification problems in different viewpoints independently, and further the models constructed with different sets of meta-features will be complementary with each other and applicable for ensemble. This paper proposes an ensemble learning-based algorithm recommendation method. To evaluate the proposed recommendation method, extensive experiments with 13 well-known candidate classification algorithms and five different kinds of meta-features are conducted on 1090 benchmark classification problems. The results show the effectiveness of the proposed ensemble learning based recommendation method.
Accurate waste disposal, at the point of disposal, is crucial to fighting climate change. When materials that could be recycled or composted get diverted into landfills, they cause the emission of potent greenhouse gases such as methane. Current attempts to reduce erroneous waste disposal are expensive, inaccurate, and confusing. In this work, we propose DeepWaste, an easy-to-use mobile app, that utilizes highly optimized deep learning techniques to provide users instantaneous waste classification into trash, recycling, and compost. We experiment with several convolution neural network architectures to detect and classify waste items. Our best model, a deep learning residual neural network with 50 layers, achieves an average precision of 0.881 on the test set. We demonstrate the performance and efficiency of our app on a set of real-world images.
Functional near-infrared spectroscopy (fNIRS) is a non-invasive, low-cost method used to study the brain's blood flow pattern. Such patterns can enable us to classify performed by a subject. In recent research, most classification systems use traditional machine learning algorithms for the classification of tasks. These methods, which are easier to implement, usually suffer from low accuracy. Further, a complex pre-processing phase is required for data preparation before implementing traditional machine learning methods. The proposed system uses a Bi-Directional LSTM based deep learning architecture for task classification, including mental arithmetic, motor imagery, and idle state using fNIRS data. Further, this system will require less pre-processing than the traditional approach, saving time and computational resources while obtaining an accuracy of 81.48\%, which is considerably higher than the accuracy obtained using conventional machine learning algorithms for the same data set.
Functional near-infrared spectroscopy (fNIRS) is a non-invasive, economical method used to study its blood flow pattern. These patterns can be used to classify tasks a subject is performing. Currently, most of the classification systems use simple machine learning solutions for the classification of tasks. These conventional machine learning methods, which are easier to implement and interpret, usually suffer from low accuracy and undergo a complex preprocessing phase before network training. The proposed method converts the raw fNIRS time series data into an image using Gramian Angular Summation Field. A Deep Convolutional Neural Network (CNN) based architecture is then used for task classification, including mental arithmetic, motor imagery, and idle state. Further, this method can eliminate the feature selection stage, which affects the traditional classifiers' performance. This system obtained 87.14% average classification accuracy higher than any other method for the dataset.
On-device Deep Neural Networks (DNNs) have recently gained more attention due to the increasing computing power of the mobile devices and the number of applications in Computer Vision (CV), Natural Language Processing (NLP), and Internet of Things (IoTs). Unfortunately, the existing efficient convolutional neural network (CNN) architectures designed for CV tasks are not directly applicable to NLP tasks and the tiny Recurrent Neural Network (RNN) architectures have been designed primarily for IoT applications. In NLP applications, although model compression has seen initial success in on-device text classification, there are at least three major challenges yet to be addressed: adversarial robustness, explainability, and personalization. Here we attempt to tackle these challenges by designing a new training scheme for model compression and adversarial robustness, including the optimization of an explainable feature mapping objective, a knowledge distillation objective, and an adversarially robustness objective. The resulting compressed model is personalized using on-device private training data via fine-tuning. We perform extensive experiments to compare our approach with both compact RNN (e.g., FastGRNN) and compressed RNN (e.g., PRADO) architectures in both natural and adversarial NLP test settings.
Most machine learning algorithms, such as classification or regression, treat the individual data point as the object of interest. Here we consider extending machine learning algorithms to operate on groups of data points. We suggest treating a group of data points as an i.i.d. sample set from an underlying feature distribution for that group. Our approach employs kernel machines with a kernel on i.i.d. sample sets of vectors. We define certain kernel functions on pairs of distributions, and then use a nonparametric estimator to consistently estimate those functions based on sample sets. The projection of the estimated Gram matrix to the cone of symmetric positive semi-definite matrices enables us to use kernel machines for classification, regression, anomaly detection, and low-dimensional embedding in the space of distributions. We present several numerical experiments both on real and simulated datasets to demonstrate the advantages of our new approach.
Graph classification is a critical research problem in many applications from different domains. In order to learn a graph classification model, the most widely used supervision component is an output layer together with classification loss (e.g.,cross-entropy loss together with softmax or margin loss). In fact, the discriminative information among instances are more fine-grained, which can benefit graph classification tasks. In this paper, we propose the novel Label Contrastive Coding based Graph Neural Network (LCGNN) to utilize label information more effectively and comprehensively. LCGNN still uses the classification loss to ensure the discriminability of classes. Meanwhile, LCGNN leverages the proposed Label Contrastive Loss derived from self-supervised learning to encourage instance-level intra-class compactness and inter-class separability. To power the contrastive learning, LCGNN introduces a dynamic label memory bank and a momentum updated encoder. Our extensive evaluations with eight benchmark graph datasets demonstrate that LCGNN can outperform state-of-the-art graph classification models. Experimental results also verify that LCGNN can achieve competitive performance with less training data because LCGNN exploits label information comprehensively.
Origami is becoming more and more relevant to research. However, there is no public dataset yet available and there hasn't been any research on this topic in machine learning. We constructed an origami dataset using images from the multimedia commons and other databases. It consists of two subsets: one for classification of origami images and the other for difficulty estimation. We obtained 16000 images for classification (half origami, half other objects) and 1509 for difficulty estimation with $3$ different categories (easy: 764, intermediate: 427, complex: 318). The data can be downloaded at: https://github.com/multimedia-berkeley/OriSet. Finally, we provide machine learning baselines.
Anomaly detection systems need to consider a lot of information when scanning for anomalies. One example is the context of the process in which an anomaly might occur, because anomalies for one process might not be anomalies for a different one. Therefore data -- such as system events -- need to be assigned to the program they originate from. This paper investigates whether it is possible to infer from a list of system events the program whose behavior caused the occurrence of these system events. To that end, we model transition probabilities between non-equivalent events and apply the $k$-nearest neighbors algorithm. This system is evaluated on non-malicious, real-world data using four different evaluation scores. Our results suggest that the approach proposed in this paper is capable of correctly inferring program names from system events.
Automatic Speech Recognition (ASR) systems are evaluated using Word Error Rate (WER), which is calculated by comparing the number of errors between the ground truth and the transcription of the ASR system. This calculation, however, requires manual transcription of the speech signal to obtain the ground truth. Since transcribing audio signals is a costly process, Automatic WER Evaluation (e-WER) methods have been developed to automatically predict the WER of a speech system by only relying on the transcription and the speech signal features. While WER is a continuous variable, previous works have shown that positing e-WER as a classification problem is more effective than regression. However, while converting to a classification setting, these approaches suffer from heavy class imbalance. In this paper, we propose a new balanced paradigm for e-WER in a classification setting. Within this paradigm, we also propose WER-BERT, a BERT based architecture with speech features for e-WER. Furthermore, we introduce a distance loss function to tackle the ordinal nature of e-WER classification. The proposed approach and paradigm are evaluated on the Librispeech dataset and a commercial (black box) ASR system, Google Cloud's Speech-to-Text API. The results and experiments demonstrate that WER-BERT establishes a new state-of-the-art in automatic WER estimation.
This article introduces a multiple classifier method to improve the performance of concatenate-designed neural networks, such as ResNet and DenseNet, with the purpose to alleviate the pressure on the final classifier. We give the design of the classifiers, which collects the features produced between the network sets, and present the constituent layers and the activation function for the classifiers, to calculate the classification score of each classifier. We use the L2 normalization method to obtain the classifier score instead of the Softmax normalization. We also determine the conditions that can enhance convergence. As a result, the proposed classifiers are able to improve the accuracy in the experimental cases significantly, and show that the method not only has better performance than the original models, but also produces faster convergence. Moreover, our classifiers are general and can be applied to all classification related concatenate-designed network models.
Deep learning has great potential for accurate detection and classification of diseases with medical imaging data, but the performance is often limited by the number of training datasets and memory requirements. In addition, many deep learning models are considered a "black-box," thereby often limiting their adoption in clinical applications. To address this, we present a successive subspace learning model, termed VoxelHop, for accurate classification of Amyotrophic Lateral Sclerosis (ALS) using T2-weighted structural MRI data. Compared with popular convolutional neural network (CNN) architectures, VoxelHop has modular and transparent structures with fewer parameters without any backpropagation, so it is well-suited to small dataset size and 3D imaging data. Our VoxelHop has four key components, including (1) sequential expansion of near-to-far neighborhood for multi-channel 3D data; (2) subspace approximation for unsupervised dimension reduction; (3) label-assisted regression for supervised dimension reduction; and (4) concatenation of features and classification between controls and patients. Our experimental results demonstrate that our framework using a total of 20 controls and 26 patients achieves an accuracy of 93.48$\%$ and an AUC score of 0.9394 in differentiating patients from controls, even with a relatively small number of datasets, showing its robustness and effectiveness. Our thorough evaluations also show its validity and superiority to the state-of-the-art 3D CNN classification methods. Our framework can easily be generalized to other classification tasks using different imaging modalities.
In highway scenarios, an alert human driver will typically anticipate early cut-in/cut-out maneuvers of surrounding vehicles using visual cues mainly. Autonomous vehicles must anticipate these situations at an early stage too, to increase their safety and efficiency. In this work, lane-change recognition and prediction tasks are posed as video action recognition problems. Up to four different two-stream-based approaches, that have been successfully applied to address human action recognition, are adapted here by stacking visual cues from forward-looking video cameras to recognize and anticipate lane-changes of target vehicles. We study the influence of context and observation horizons on performance, and different prediction horizons are analyzed. The different models are trained and evaluated using the PREVENTION dataset. The obtained results clearly demonstrate the potential of these methodologies to serve as robust predictors of future lane-changes of surrounding vehicles proving an accuracy higher than 90% in time horizons of between 1-2 seconds.
Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis. This paper studies the effectiveness of self-supervised learning as a pretraining strategy for medical image classification. We conduct experiments on two distinct tasks: dermatology skin condition classification from digital camera images and multi-label chest X-ray classification, and demonstrate that self-supervised learning on ImageNet, followed by additional self-supervised learning on unlabeled domain-specific medical images significantly improves the accuracy of medical image classifiers. We introduce a novel Multi-Instance Contrastive Learning (MICLe) method that uses multiple images of the underlying pathology per patient case, when available, to construct more informative positive pairs for self-supervised learning. Combining our contributions, we achieve an improvement of 6.7% in top-1 accuracy and an improvement of 1.1% in mean AUC on dermatology and chest X-ray classification respectively, outperforming strong supervised baselines pretrained on ImageNet. In addition, we show that big self-supervised models are robust to distribution shift and can learn efficiently with a small number of labeled medical images.
A graph's spectral wavelet signature determines a filtration, and consequently an associated set of extended persistence diagrams. We propose a framework that optimises the choice of wavelet for a dataset of graphs, such that their associated persistence diagrams capture features of the graphs that are best suited to a given data science problem. Since the spectral wavelet signature of a graph is derived from its Laplacian, our framework encodes geometric properties of graphs in their associated persistence diagrams and can be applied to graphs without a priori node attributes. We apply our framework to graph classification problems and obtain performances competitive with other persistence-based architectures. To provide the underlying theoretical foundations, we extend the differentiability result for ordinary persistent homology to extended persistent homology.
We consider the problem of multi-label classification where the labels lie in a hierarchy. However, unlike most existing works in hierarchical multi-label classification, we do not assume that the label-hierarchy is known. Encouraged by the recent success of hyperbolic embeddings in capturing hierarchical relations, we propose to jointly learn the classifier parameters as well as the label embeddings. Such a joint learning is expected to provide a twofold advantage: i) the classifier generalizes better as it leverages the prior knowledge of existence of a hierarchy over the labels, and ii) in addition to the label co-occurrence information, the label-embedding may benefit from the manifold structure of the input datapoints, leading to embeddings that are more faithful to the label hierarchy. We propose a novel formulation for the joint learning and empirically evaluate its efficacy. The results show that the joint learning improves over the baseline that employs label co-occurrence based pre-trained hyperbolic embeddings. Moreover, the proposed classifiers achieve state-of-the-art generalization on standard benchmarks. We also present evaluation of the hyperbolic embeddings obtained by joint learning and show that they represent the hierarchy more accurately than the other alternatives.