Scene Image Classification Using Reduced Virtual Feature Representation in Sparse Framework

Most machine learning algorithms assume stationary environments, require a large number of training examples in advance, and begin the learning from scratch. In contrast, humans learn in changing environments with sequential training examples and leverage prior knowledge in new situations. To deal with real-world problems in changing environments, the ability to make human-like quick responses must be developed in machines. Many researchers have presented learning systems that assume the presence of hidden context and concept drift. In particular, several systems have been proposed that use ensembles of classifiers on sequential chunks of training examples. These systems can respond to gradual changes in large-scale data streams but have problems responding to sudden changes and leveraging prior knowledge of recurring contexts. Moreover, these are not pure online learning systems. We propose an online learning system that uses an ensemble of classifiers suited to recent training examples. We use experiments to show that this system can leverage prior knowledge of recurring contexts and is robust against various noise levels and types of drift.

We present a new method of learning control policies that successfully operate under unknown dynamic models. We create such policies by leveraging a large number of training examples that are generated using a physical simulator. Our system is made of two components: a Universal Policy (UP) and a function for Online System Identification (OSI). We describe our control policy as universal because it is trained over a wide array of dynamic models. These variations in the dynamic model may include differences in mass and inertia of the robots' components, variable friction coefficients, or unknown mass of an object to be manipulated. By training the Universal Policy with this variation, the control policy is prepared for a wider array of possible conditions when executed in an unknown environment. The second part of our system uses the recent state and action history of the system to predict the dynamics model parameters mu. The value of mu from the Online System Identification is then provided as input to the control policy (along with the system state). Together, UP-OSI is a robust control policy that can be used across a wide range of dynamic models, and that is also responsive to sudden changes in the environment. We have evaluated the performance of this system on a variety of tasks, including the problem of cart-pole swing-up, the double inverted pendulum, locomotion of a hopper, and block-throwing of a manipulator. UP-OSI is effective at these tasks across a wide range of dynamic models. Moreover, when tested with dynamic models outside of the training range, UP-OSI outperforms the Universal Policy alone, even when UP is given the actual value of the model dynamics. In addition to the benefits of creating more robust controllers, UP-OSI also holds out promise of narrowing the Reality Gap between simulated and real physical systems.

Cloud detection in satellite images using multi-objective social spider optimization

Humans are natural face recognition experts, far out-performing current automated face recognition algorithms, especially in naturalistic, “in the wild” settings. However, a striking feature of human face recognition is that we are dramatically better at recognizing highly familiar faces, presumably because we can leverage large amounts of past experience with the appearance of an individual to aid future recognition. Meanwhile, the analogous situation in automated face recognition, where a large number of training examples of an individual are available, has been largely underexplored, in spite of the increasing relevance of this setting in the age of social media. Inspired by these observations, we propose to explicitly learn enhanced face representations on a per-individual basis, and we present two methods enabling this approach. By learning and operating within person-specific representations, we are able to significantly outperform the previous state-of-the-art on PubFig83, a challenging benchmark for familiar face recognition in the wild, using a novel method for learning representations in deep visual hierarchies. We suggest that such person-specific representations aid recognition by introducing an intermediate form of regularization to the problem.

Lifelong Machine Learning (or Lifelong Learning) is an advanced machine learning paradigm that learns continuously, accumulates the knowledge learned in previous tasks, and uses it to help future learning. In the process, the learner becomes more and more knowledgeable and effective at learning. This learning ability is one of the hallmarks of human intelligence. However, the current dominant machine learning paradigm learns in isolation: given a training dataset, it runs a machine learning algorithm on the dataset to produce a model. It makes no attempt to retain the learned knowledge and use it in future learning. Although this isolated learning paradigm has been very successful, it requires a large number of training examples, and is only suitable for well-defined and narrow tasks. In comparison, we humans can learn effectively with a few examples because we have accumulated so much knowledge in the past which enables us to learn with little data or effort. Lifelong learning aims to achieve this capability. As statistical machine learning matures, it is time to make a major effort to break the isolated learning tradition and to study lifelong learning to bring machine learning to new heights. Applications such as intelligent assistants, chatbots, and physical robots that interact with humans and systems in real-life environments are also calling for such lifelong learning capabilities. Without the ability to accumulate the learned knowledge and use it to learn more knowledge incrementally, a system will probably never be truly intelligent. This book serves as an introductory text and survey to lifelong learning.

Few-shot Learning (FSL) methods are being adopted in settings where data is not abundantly available. This is especially seen in medical domains where the annotations are expensive to obtain. Deep Neural Networks have been shown to be vulnerable to adversarial attacks. This is even more severe in the case of FSL due to the lack of a large number of training examples. In this paper, we provide a framework to make few-shot segmentation models adversarially robust in the medical domain where such attacks can severely impact the decisions made by clinicians who use them. We propose a novel robust few-shot segmentation framework, Prototypical Neural Ordinary Differential Equation (PNODE), that provides defense against gradient-based adversarial attacks. We show that our framework is more robust compared to traditional adversarial defense mechanisms such as adversarial training. Adversarial training involves increased training time and shows robustness to limited types of attacks depending on the type of adversarial examples seen during training. Our proposed framework generalises well to common adversarial attacks like FGSM, PGD and SMIA while having the model parameters comparable to the existing few-shot segmentation models. We show the effectiveness of our proposed approach on three publicly available multi-organ segmentation datasets in both in-domain and cross-domain settings by attacking the support and query sets without the need for ad-hoc adversarial training.KeywordsFew-shot segmentationNeural-ODEAdversarial robustness

Reviewing video from wireless capsule endoscopy is a tedious work that requires concentration for extended hours. Computer algorithms are sought to reduce the review time and large number of training examples, to reduce the generalization error of machine learning algorithms. Therefore efficient and scalable approaches are needed which can modify knowledge structures in an incremental fashion without having to revisit all previously processed data. This paper proposes a novel incremental learning method for SVMs. The intuition is that the samples within the skin are retained alone in training. When additional samples are provided, they will be used together with the skin of the convex hull constructed from previous dataset. This result in much less number of instances and are used in incremental steps of the training process. Experiments were performed to segment frames of capsule endoscopy videos into four sections of gastrointestinal tract.

We introduce a Convolutional Neural Network (CNN) to post-process recordings obtained by means of Background Oriented Schlieren (BOS), a popular technique to visualize compressible/convective flows. To reconstruct BOS image deformation, we devised a lightweight network (LIMA) that has comparatively fewer parameters to train, allowing the deployment of the network on embedded GPU hardware. To train the CNN, we introduce a novel strategy based on the generation of synthetic images with random, irrotational displacement field that mimic those provided by real BOS recording. This allows us to generate a large number of training examples at minimal computational cost. To assess the accuracy of the reconstructed displacement, we consider test cases consisting of synthetic images with sinusoidal displacement as well as images obtained in a real experimental study of flow past and inside a heated hollow hemisphere. By comparing the prediction of the CNN with conventional post-processing techniques such as Direct Image Correlation (DIC) and Particle Image Velocimetry (PIV) cross-correlation, we show that LIMA gives more accurate and robust results for the synthetic example. When applied to the recordings from the real experiment, all methods provide consistent deformation fields. As they offer similar or better accuracy at a fraction of the computational costs, properly designed CNNs offer a valuable alternative to conventional post-processing techniques for BOS experiments.

An important problem in pattern recognition is that of pattern classification. The objective of classification is to determine a discriminant function which is consistent with the given training examples and performs reasonably well on an unlabeled test set of examples. The degree of performance of the classifier on the test examples, known as its generalization performance, is an important issue in the design of the classifier. It has been established that a good generalization performance can be achieved by providing the learner with a sufficiently large number of discriminative training examples. However, in many domains, it is infeasible or expensive to obtain a sufficiently large training set. Various mechanisms have been proposed in literature to combat this problem. Active Learning techniques (Angluin, 1998; Seung, Opper, & Sompolinsky, 1992) reduce the number of training examples required by carefully choosing discriminative training examples. Bootstrapping (Efron, 1979; Hamamoto, Uchimura & Tomita, 1997) and other pattern synthesis techniques generate a synthetic training set from the given training set. We present some of these techniques and propose some general mechanisms for pattern synthesis. Request access from your librarian to read this chapter's full text.

A central problem in learning is selection of an appropriate model. This is typically done by estimating the unknown generalization errors of a set of models to be selected from and then choosing the model with minimal generalization error estimate. In this article, we discuss the problem of model selection and generalization error estimation in the context of kernel regression models, e.g., kernel ridge regression, kernel subset regression or Gaussian process regression. Previously, a non-asymptotic generalization error estimator called the subspace information criterion (SIC) was proposed, that could be successfully applied to finite dimensional subspace models. SIC is an unbiased estimator of the generalization error for the finite sample case under the conditions that the learning target function belongs to a specified reproducing kernel Hilbert space (RKHS) H and the reproducing kernels centered on training sample points span the whole space H. These conditions hold only if dim H < l, where l < ∞ is the number of training examples. Therefore, SIC could be applied only to finite dimensional RKHSs. In this paper, we extend the range of applicability of SIC, and show that even if the reproducing kernels centered on training sample points do not span the whole space H, SIC is an unbiased estimator of an essential part of the generalization error. Our extension allows the use of any RKHSs including infinite dimensional ones, i.e., richer function classes commonly used in Gaussian processes, support vector machines or boosting. We further show that when the kernel matrix is invertible, SIC can be expressed in a much simpler form, making its computation highly efficient. In computer simulations on ridge parameter selection with real and artificial data sets, SIC is compared favorably with other standard model selection techniques for instance leave-one-out cross-validation or an empirical Bayesian method.

Modern classification techniques perform well when the number of training examples exceed the number of features. If, however, the number of features greatly exceed the number of training examples, then these same techniques can fail. To address this problem, we present a hierarchical Bayesian framework that shares information between features by modeling similarities between their parameters. We believe this approach is applicable to many sparse, high dimensional problems and especially relevant to those with both spatial and temporal components. One such problem is fMRI time series, and we present a case study that shows how we can successfully classify in this domain with 80,000 original features and only 2 training examples per class.

Image understanding and scene classification are keystone tasks in computer vision. The development of technologies and profusion of existing datasets open a wide room for improvement in the image classification and recognition research area. Notwithstanding the optimal performance of exiting machine learning models in image understanding and scene classification, there are still obstacles to overcome. All models are data-dependent that can only classify samples close to the training set. Moreover, these models require large data for training and learning. The first problem is solved by few-shot learning, which achieves optimal performance in object detection and classification but with a lack of eligible attention in the scene classification task. Motivated by these findings, in this paper, we introduce two models for few-shot learning in scene classification. In order to trace the behavior of those models, we also introduce two datasets (MiniSun; MiniPlaces) for image scene classification. Experimental results show that the proposed models outperform the benchmark approaches in respect of classification accuracy.

Phase unwrapping is one of the toughest problems in interferometric SAR processing. The main difficulties arise from the presence of point-like error sources, called residues, which occur mainly in close couples due to phase noise. We present an assessment of a local approach to the resolution of these problems by means of a neural network. Using a multi-layer perceptron, trained with the back- propagation scheme on a series of simulated phase images, fashion the best pairing strategies for close residue couples. Results show that god efficiencies and accuracies can have been obtained, provided a sufficient number of training examples are supplied. Results show that good efficiencies and accuracies can be obtained, provided a sufficient number of training examples are supplied. The technique is tested also on real SAR ERS-1/2 tandem interferometric images of the Matera test site, showing a good reduction of the residue density. The better results obtained by use of the neural network as far as local criteria are adopted appear justified given the probabilistic nature of the noise process on SAR interferometric phase fields and allows to outline a specifically tailored implementation of the neural network approach as a very fast pre-processing step intended to decrease the residue density and give sufficiently clean images to be processed further by more conventional techniques.

We propose a novel algorithm for the task of supervised discriminative distance learning by nonlinearly embedding vectors into a low dimensional Euclidean space. We work in the challenging setting where supervision is with constraints on similar and dissimilar pairs while training. The proposed method is derived by an approximate kernelization of a linear Mahalanobis-like distance metric learning algorithm and can also be seen as a kernel neural network. The number of model parameters and test time evaluation complexity of the proposed method are O(dD) where D is the dimensionality of the input features and d is the dimension of the projection space -- this is in contrast to the usual kernelization methods as, unlike them, the complexity does not scale linearly with the number of training examples. We propose a stochastic gradient based learning algorithm which makes the method scalable (w.r.t. the number of training examples), while being nonlinear. We train the method with up to half a million training pairs of 4096 dimensional CNN features. We give empirical comparisons with relevant baselines on seven challenging datasets for the task of low dimensional semantic category based image retrieval.

Segmentation-based methods have achieved great success for arbitrary shape text detection. However, separating neighboring text instances is still one of the most challenging problems due to the complexity of texts in scene images. In this article, we propose an innovative kernel proposal network (dubbed KPN) for arbitrary shape text detection. The proposed KPN can separate neighboring text instances by classifying different texts into instance-independent feature maps, meanwhile avoiding the complex aggregation process existing in segmentation-based arbitrary shape text detection methods. To be concrete, our KPN will predict a Gaussian center map for each text image, which will be used to extract a series of candidate kernel proposals (i.e., dynamic convolution kernel) from the embedding feature maps according to their corresponding keypoint positions. To enforce the independence between kernel proposals, we propose a novel orthogonal learning loss (OLL) via orthogonal constraints. Specifically, our kernel proposals contain important self-information learned by network and location information by position embedding. Finally, kernel proposals will individually convolve all embedding feature maps for generating individual embedded maps of text instances. In this way, our KPN can effectively separate neighboring text instances and improve the robustness against unclear boundaries. To the best of our knowledge, our work is the first to introduce the dynamic convolution kernel strategy to efficiently and effectively tackle the adhesion problem of neighboring text instances in text detection. Experimental results on challenging datasets verify the impressive performance and efficiency of our method. The code and model are available at https://github.com/GXYM/KPN.