Search

Deep Neural Networks have received considerable attention in recent years. As the complexity of network architecture increases in relation to the task complexity, it becomes harder to manually craft an optimal neural network architecture and train it to convergence. As such, Neural Architecture Search (NAS) is becoming far more prevalent within computer vision research, especially when the construction of efficient, smaller network architectures is becoming an increasingly important area of research, for which NAS is well suited. However, despite their promise, contemporary and end-to-end NAS pipeline require vast computational training resources. In this paper, we present a comprehensive overview of contemporary NAS approaches with respect to image classification, object detection, and image segmentation. We adopt consistent terminology to overcome contradictions common within existing NAS literature. Furthermore, we identify and compare current performance limitations in addition to highlighting directions for future NAS research. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is a popular machine learning method which can flexibly simulate the relationships of real-world classification applications. When facing problems ( i.e. , data sets) with a smaller number of samples ( i.e. , instances), ELM may often result in the overfitting trouble. In this paper, we propose a new Instance Cloned Extreme Learning Machine (IC-ELM for short) which can handle numerous different classification problems. IC-ELM uses an instance cloning method to balance the input data’s distribution and extend the training data set, which alleviates the overfitting issue and enhances the testing classification accuracy. Experiments and comparisons on 20 UCI data sets, and validations on image and text classification applications, demonstrate that IC-ELM is able to achieve superior results compared to the original ELM algorithm and its variants, as well as several other classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

In this paper, a cost-sensitive learning algorithm is developed to train hierarchical tree classifiers for large-scale image classification application (i.e., categorizing large-scale images into thousands of object classes). A visual tree is first constructed for organizing large numbers of object classes hierarchically and identifying inter-related learning tasks automatically. For the fine-grained object classes at the sibling leaf nodes, they share significant common visual properties but still contain subtle visual differences, thus a multi-task structural learning algorithm is developed to train their inter-related classifiers jointly to enhance their discrimination power. For the coarse-grained categories (i.e., groups of visually similar object classes) at the sibling non-leaf nodes, a hierarchical learning algorithm is developed to leverage tree structure (by adding two inter-level constraints) to train their inter-related classifiers jointly and control inter-level error propagation effectively. To achieve more robust detection of large numbers of object classes, a visual forest is learned by combining multiple visual trees (for different configurations) and their hierarchical tree classifiers. By penalizing various types of misclassification errors differently, a cost-sensitive learning approach is further developed to detect the appearances of new object classes accurately, and an incremental learning algorithm is developed to achieve more effective training of the discriminative classifiers for new object classes. Our experimental results have demonstrated that our cost-sensitive hierarchical learning algorithm can achieve very competitive results on both classification accuracy and computational efficiency as compared with other state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a new discriminative linear regression approach to adaptation of a discriminatively trained prototype-based classifier for Chinese OCR. A so-called sample separation margin based minimum classification error criterion is used in both classifier training and adaptation, while an Rprop algorithm is used for optimizing the objective function. Formulations for both model-space and feature-space adaptation are presented. The effectiveness of the proposed approach is confirmed by a series of experiments for adaptation of font styles and low-quality text, respectively. [Copyright &y& Elsevier]