In image classification tasks, the ability of deep CNNs to deal with complex image data has proven to be unrivalled. However, they require large amounts of labeled training data to reach their full potential. In specialised domains such as healthcare, labeled data can be difficult and expensive to obtain. Active Learning aims to alleviate this problem, by reducing the amount of labelled data needed for a specific task while delivering satisfactory performance. We propose DEBAL, a new active learning strategy designed for deep neural networks. This method improves upon the current state-of-the-art deep Bayesian active learning method, which suffers from the mode collapse problem. We correct for this deficiency by making use of the expressive power and statistical properties of model ensembles. Our proposed method manages to capture superior data uncertainty, which translates into improved classification performance. We demonstrate empirically that our ensemble method yields faster convergence of CNNs trained on the MNIST and CIFAR-10 datasets.
Examplers of a face are formed from multiple gallery images of a person and are used in the process of classification of a test image. We incorporate such examplers in forming a biologically inspired local binary decisions on similarity based face recognition method. As opposed to single model approaches such as face averages the exampler based approach results in higher recognition accu- racies and stability. Using multiple training samples per person, the method shows the following recognition accuracies: 99.0% on AR, 99.5% on FERET, 99.5% on ORL, 99.3% on EYALE, 100.0% on YALE and 100.0% on CALTECH face databases. In addition to face recognition, the method also detects the natural variability in the face images which can find application in automatic tagging of face images.
A key recent advance in face recognition models a test face image as a sparse linear combination of a set of training face images. The resulting sparse representations have been shown to possess robustness against a variety of distortions like random pixel corruption, occlusion and disguise. This approach however makes the restrictive (in many scenarios) assumption that test faces must be perfectly aligned (or registered) to the training data prior to classification. In this paper, we propose a simple yet robust local block-based sparsity model, using adaptively-constructed dictionaries from local features in the training data, to overcome this misalignment problem. Our approach is inspired by human perception: we analyze a series of local discriminative features and combine them to arrive at the final classification decision. We propose a probabilistic graphical model framework to explicitly mine the conditional dependencies between these distinct sparse local features. In particular, we learn discriminative graphs on sparse representations obtained from distinct local slices of a face. Conditional correlations between these sparse features are first discovered (in the training phase), and subsequently exploited to bring about significant improvements in recognition rates. Experimental results obtained on benchmark face databases demonstrate the effectiveness of the proposed algorithms in the presence of multiple registration errors (such as translation, rotation, and scaling) as well as under variations of pose and illumination.
The paper will present a novel approach for solving face recognition problem. Our method combines 2D Principal Component Analysis (2DPCA), one of the prominent methods for extracting feature vectors, and Support Vector Machine (SVM), the most powerful discriminative method for classification. Experiments based on proposed method have been conducted on two public data sets FERET and AT&T; the results show that the proposed method could improve the classification rates.
Here an efficient fusion technique for automatic face recognition has been presented. Fusion of visual and thermal images has been done to take the advantages of thermal images as well as visual images. By employing fusion a new image can be obtained, which provides the most detailed, reliable, and discriminating information. In this method fused images are generated using visual and thermal face images in the first step. In the second step, fused images are projected into eigenspace and finally classified using a radial basis function neural network. In the experiments Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database benchmark for thermal and visual face images have been used. Experimental results show that the proposed approach performs well in recognizing unknown individuals with a maximum success rate of 96%.
This paper presents a novel approach to handle the challenges of face recognition. In this work thermal face images are considered, which minimizes the affect of illumination changes and occlusion due to moustache, beards, adornments etc. The proposed approach registers the training and testing thermal face images in polar coordinate, which is capable to handle complicacies introduced by scaling and rotation. Polar images are projected into eigenspace and finally classified using a multi-layer perceptron. In the experiments we have used Object Tracking and Classification Beyond Visible Spectrum (OTCBVS) database benchmark thermal face images. Experimental results show that the proposed approach significantly improves the verification and identification performance and the success rate is 97.05%.
In this paper, the problem of automatic Gabor wavelet selection for face recognition is tackled by introducing an automatic algorithm based on Parallel AdaBoosting method. Incorporating mutual information into the algorithm leads to the selection procedure not only based on classification accuracy but also on efficiency. Effective image features are selected by using properly chosen Gabor wavelets optimised with Parallel AdaBoost method and mutual information to get high recognition rates with low computational cost. Experiments are conducted using the well-known FERET face database. In proposed framework, memory and computation costs are reduced significantly and high classification accuracy is obtained.
Recently, Adaboost has been widely used to improve the accuracy of any given learning algorithm. In this paper we focus on designing an algorithm to employ combination of Adaboost with Support Vector Machine as weak component classifiers to be used in Face Detection Task. To obtain a set of effective SVM-weaklearner Classifier, this algorithm adaptively adjusts the kernel parameter in SVM instead of using a fixed one. Proposed combination outperforms in generalization in comparison with SVM on imbalanced classification problem. The proposed here method is compared, in terms of classification accuracy, to other commonly used Adaboost methods, such as Decision Trees and Neural Networks, on CMU+MIT face database. Results indicate that the performance of the proposed method is overall superior to previous Adaboost approaches.
Applications such as face recognition that deal with high-dimensional data need a mapping technique that introduces representation of low-dimensional features with enhanced discriminatory power and a proper classifier, able to classify those complex features. Most of traditional Linear Discriminant Analysis suffer from the disadvantage that their optimality criteria are not directly related to the classification ability of the obtained feature representation. Moreover, their classification accuracy is affected by the "small sample size" problem which is often encountered in FR tasks. In this short paper, we combine nonlinear kernel based mapping of data called KDDA with Support Vector machine classifier to deal with both of the shortcomings in an efficient and cost effective manner. The proposed here method is compared, in terms of classification accuracy, to other commonly used FR methods on UMIST face database. Results indicate that the performance of the proposed method is overall superior to those of traditional FR approaches, such as the Eigenfaces, Fisherfaces, and D-LDA methods and traditional linear classifiers.
Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically principled, BNNs require approximations to be applied to large-scale problems, where both performance and uncertainty estimation are crucial. In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep BNN. We conduct a series of large-scale visual active learning experiments to evaluate DPEs on classification with the CIFAR-10, CIFAR-100 and ImageNet datasets, and semantic segmentation with the BDD100k dataset. Our models require significantly less training data to achieve competitive performances, and steadily improve upon strong active learning baselines as the annotation budget is increased.
Fully-connected Conditional Random Field (CRF) is often used as post-processing to refine voxel classification results by encouraging spatial coherence. In this paper, we propose a new end-to-end training method called Posterior-CRF. In contrast with previous approaches which use the original image intensity in the CRF, our approach applies 3D, fully connected CRF to the posterior probabilities from a CNN and optimizes both CNN and CRF together. The experiments on white matter hyperintensities segmentation demonstrate that our method outperforms CNN, post-processing CRF and different end-to-end training CRF approaches.
Graphs are complex objects that do not lend themselves easily to typical learning tasks. Recently, a range of approaches based on graph kernels or graph neural networks have been developed for graph classification and for representation learning on graphs in general. As the developed methodologies become more sophisticated, it is important to understand which components of the increasingly complex methods are necessary or most effective. As a first step, we develop a simple yet meaningful graph representation, and explore its effectiveness in graph classification. We test our baseline representation for the graph classification task on a range of graph datasets. Interestingly, this simple representation achieves similar performance as the state-of-the-art graph kernels and graph neural networks for non-attributed graph classification. Its performance on classifying attributed graphs is slightly weaker as it does not incorporate attributes. However, given its simplicity and efficiency, we believe that it still serves as an effective baseline for attributed graph classification. Our graph representation is efficient (linear-time) to compute. We also provide a simple connection with the graph neural networks. Note that these observations are only for the task of graph classification while existing methods are often designed for a broader scope including node embedding and link prediction. The results are also likely biased due to the limited amount of benchmark datasets available. Nevertheless, the good performance of our simple baseline calls for the development of new, more comprehensive benchmark datasets so as to better evaluate and analyze different graph learning methods. Furthermore, given the computational efficiency of our graph summary, we believe that it is a good candidate as a baseline method for future graph classification (or even other graph learning) studies.
Due to cellular heterogeneity, cell nuclei classification, segmentation, and detection from pathological images are challenging tasks. In the last few years, Deep Convolutional Neural Networks (DCNN) approaches have been shown state-of-the-art (SOTA) performance on histopathological imaging in different studies. In this work, we have proposed different advanced DCNN models and evaluated for nuclei classification, segmentation, and detection. First, the Densely Connected Recurrent Convolutional Network (DCRN) model is used for nuclei classification. Second, Recurrent Residual U-Net (R2U-Net) is applied for nuclei segmentation. Third, the R2U-Net regression model which is named UD-Net is used for nuclei detection from pathological images. The experiments are conducted with different datasets including Routine Colon Cancer(RCC) classification and detection dataset, and Nuclei Segmentation Challenge 2018 dataset. The experimental results show that the proposed DCNN models provide superior performance compared to the existing approaches for nuclei classification, segmentation, and detection tasks. The results are evaluated with different performance metrics including precision, recall, Dice Coefficient (DC), Means Squared Errors (MSE), F1-score, and overall accuracy. We have achieved around 3.4% and 4.5% better F-1 score for nuclei classification and detection tasks compared to recently published DCNN based method. In addition, R2U-Net shows around 92.15% testing accuracy in term of DC. These improved methods will help for pathological practices for better quantitative analysis of nuclei in Whole Slide Images(WSI) which ultimately will help for better understanding of different types of cancer in clinical workflow.
We propose a method to classify cardiac pathology based on a novel approach to extract image derived features to characterize the shape and motion of the heart. An original semi-supervised learning procedure, which makes efficient use of a large amount of non-segmented images and a small amount of images segmented manually by experts, is developed to generate pixel-wise apparent flow between two time points of a 2D+t cine MRI image sequence. Combining the apparent flow maps and cardiac segmentation masks, we obtain a local apparent flow corresponding to the 2D motion of myocardium and ventricular cavities. This leads to the generation of time series of the radius and thickness of myocardial segments to represent cardiac motion. These time series of motion features are reliable and explainable characteristics of pathological cardiac motion. Furthermore, they are combined with shape-related features to classify cardiac pathologies. Using only nine feature values as input, we propose an explainable, simple and flexible model for pathology classification. On ACDC training set and testing set, the model achieves 95% and 94% respectively as classification accuracy. Its performance is hence comparable to that of the state-of-the-art. Comparison with various other models is performed to outline some advantages of our model.
Perceptual capabilities of artificial systems have come a long way since the advent of deep learning. These methods have proven to be effective, however they are not as efficient as their biological counterparts. Visual attention is a set of mechanisms that are employed in biological visual systems to ease computational load by only processing pertinent parts of the stimuli. This paper addresses the implementation of top-down, feature-based attention in an artificial neural network by use of externally controlled neuron gating. Our results showed a 5% increase in classification accuracy on the CIFAR-10 dataset versus a non-gated version, while adding very few parameters. Our gated model also produces more reasonable errors in predictions by drastically reducing prediction of classes that belong to a different category to the true class.
Text classification is a fundamental task in NLP applications. Latest research in this field has largely been divided into two major sub-fields. Learning representations is one sub-field and learning deeper models, both sequential and convolutional, which again connects back to the representation is the other side. We posit the idea that the stronger the representation is, the simpler classifier models are needed to achieve higher performance. In this paper we propose a completely novel direction to text classification research, wherein we convert text to a representation very similar to images, such that any deep network able to handle images is equally able to handle text. We take a deeper look at the representation of documents as an image and subsequently utilize very simple convolution based models taken as is from computer vision domain. This image can be cropped, re-scaled, re-sampled and augmented just like any other image to work with most of the state-of-the-art large convolution based models which have been designed to handle large image datasets. We show impressive results with some of the latest benchmarks in the related fields. We perform transfer learning experiments, both from text to text domain and also from image to text domain. We believe this is a paradigm shift from the way document understanding and text classification has been traditionally done, and will drive numerous novel research ideas in the community.
Ordinal regression aims to classify instances into ordinal categories. In this paper, body mass index (BMI) category estimation from facial images is cast as an ordinal regression problem. In particular, noisy binary search algorithms based on pairwise comparisons are employed to exploit the ordinal relationship among BMI categories. Comparisons are performed with Siamese architectures, one of which uses the Bradley-Terry model probabilities as target. The Bradley-Terry model is an approach to describe probabilities of the possible outcomes when elements of a set are repeatedly compared with one another in pairs. Experimental results show that our approach outperforms classification and regression-based methods at estimating BMI categories.
Purpose-Optimal use of established and imaging methods, such as multiparametric magnetic resonance imaging(mpMRI) can simultaneously identify key functional parameters and provide unique imaging phenotypes of breast cancer. Therefore, we have developed and implemented a new machine-learning informatic system that integrates clinical variables, derived from imaging and clinical health records, to compare with the 21-gene array assay, OncotypeDX. Materials and methods-We tested our informatics modeling in a subset of patients (n=81) who had ER+ disease and underwent OncotypeDX gene expression and breast mpMRI testing. The machine-learning informatic method is termed Integrated Radiomic Informatic System-IRIS was applied to the mpMRI, clinical and pathologic descriptors, as well as a gene array analysis. The IRIS method using an advanced graph theoretic model and quantitative metrics. Summary statistics (mean and standard deviations) for the quantitative imaging parameters were obtained. Sensitivity and specificity and Area Under the Curve were calculated for the classification of the patients. Results-The OncotypeDX classification by IRIS model had sensitivity of 95% and specificity of 89% with AUC of 0.92. The breast lesion size was larger for the high-risk groups and lower for both low risk and intermediate risk groups. There were significant differences in PK-DCE and ADC map values in each group. The ADC map values for high- and intermediate-risk groups were significantly lower than the low-risk group. Conclusion-These initial studies provide deeper understandings of imaging features and molecular gene array OncotypeDX score. This insight provides the foundation to relate these imaging features to the assessment of treatment response for improved personalized medicine.
Poultry farms are an important contributor to the human food chain. Worldwide, humankind keeps an enormous number of domesticated birds (e.g. chickens) for their eggs and their meat, providing rich sources of low-fat protein. However, around the world, there have been growing concerns about the quality of life for the livestock in poultry farms; and increasingly vocal demands for improved standards of animal welfare. Recent advances in sensing technologies and machine learning allow the possibility of automatically assessing the health of some individual birds, and employing the lessons learned to improve the welfare for all birds. This task superficially appears to be easy, given the dramatic progress in recent years in classifying human behaviors, and given that human behaviors are presumably more complex. However, as we shall demonstrate, classifying chicken behaviors poses several unique challenges, chief among which is creating a generalizable dictionary of behaviors from sparse and noisy data. In this work we introduce a novel time series dictionary learning algorithm that can robustly learn from weakly labeled data sources.
This paper tackles the challenge of colorizing grayscale images. We take a deep convolutional neural network approach, and choose to take the angle of classification, working on a finite set of possible colors. Similarly to a recent paper, we implement a loss and a prediction function that favor realistic, colorful images rather than "true" ones. We show that a rather lightweight architecture inspired by the U-Net, and trained on a reasonable amount of pictures of landscapes, achieves satisfactory results on this specific subset of pictures. We show that data augmentation significantly improves the performance and robustness of the model, and provide visual analysis of the prediction confidence. We show an application of our model, extending the task to video colorization. We suggest a way to smooth color predictions across frames, without the need to train a recurrent network designed for sequential inputs.