The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper presents a novel approach to launch and defend against the causative and evasion attacks on machine learning classifiers. As the preliminary step, the adversary starts with an exploratory attack based on deep learning (DL) and builds a functionally equivalent classifier by polling the online target classifier with input data and observing the returned labels. Using this inferred classifier,...
The performance of deep convolution neural networks will be further enhanced with the expansion of the training data set. For the image classification tasks, it is necessary to expand the insufficient training image samples through various data augmentation methods. This paper explores the impact of various data augmentation methods on image classification tasks with deep convolution Neural network,...
Ship category recognition is one of the remote sensing applications that requires designing accurate image representation and classification models. Training these models is usually a data hungry process, that requires a lot of labeled data which are usually scarce and expensive. As unlabeled data are more abundant and relatively cheaper, transductive methods exploiting these data are highly preferred...
Nowadays the CNN is widely used in practical applications for image classification task. However the design of the CNN model is very professional work and which is very difficult for ordinary users. Besides, even for experts of CNN, to select an optimal model for specific task may still need a lot of time (to train many different models). In order to solve this problem, we proposed an automated CNN...
ELM with kernels and MapReduce have an unparalleled advantage of other similar technologies, which attract widely attention in machine learning and distributed data processing communities respectively. In this paper, we combine the advantage of ELM with kernels and MapReduce, and propose a Distributed Extreme Learning Machine with kernels based on MapReduce framework (DK-ELMM),which makes full use...
Collaborative representation based classifier (CRC) and its probabilistic improvement ProCRC have achieved satisfactory performance in many image classification applications. They, however, do not comprehensively take account of the structure characteristics of the training samples. In this paper, we present an extended probabilistic collaborative representation based classifier (EProCRC) for image...
The new advanced very high resolution (VHR) synthetic aperture radar (SAR) sensor is a kind of high-tech imaging radar developed rapidly in recent years, and it can get even less than 1 m high resolution SAR image. The feature of the VHR SAR image is different from the low or medium resolution SAR image and it contains more abundant information, so the traditional SAR image classification methods...
Deep Convolutional Neural Networks (CNN) have recently been shown to outperform previous state of the art approaches for image classification. Their success must in parts be attributed to the availability of large labeled training sets such as provided by the ImageNet benchmarking initiative. When training data is scarce, however, CNNs have proven to fail to learn descriptive features. Recent research...
Plankton image classification plays an important role in the ocean ecosystems research. Recently, a large scale database for plankton classification with over 3 million images annotated with over 100 classes was released. However, the database suffers from imbalanced class distribution in which over 90% of images belong to only 5 classes. Due to this class-imbalance problem, the existing classification...
To train a scene classifier with good generalization capability, a large number of human labeled training images are often needed. However, a large number of well-labeled training images may not always be available. To alleviate this problem, the web resources-aided scene classification framework was proposed. The present paper is a new development based on our previously proposed framework [1], with...
Object category recognition, in remote sensing imagery, usually relies on exemplar-based training. The latter is achieved by modeling intricate relationships between object categories and visual features. However, for real-world and fine grained object categories - exhibiting complex visual appearance and strong variability - these models may fail especially when training data are scarce. In this...
The quality of the training data used in a supervised image classification can impact on the accuracy of the resulting thematic map obtained. Here the effects of mis-labeled training cases on the accuracy of classifications by discriminant analysis and a support vector machine were explored. The accuracy of both classifiers varied with the amount and nature of mis-labeled training cases. In particular,...
Due to the imbalance in obtaining labeled samples for different land-cover classes, hyperspectral image classification encounters the issue of imbalanced classification. In this paper, a novel and effective method is proposed to address the imbalanced learning problem in hyperspectral image classification, which combines support vector machine (SVM) and sampling strategy. The main novelty and contribution...
One of the main problems in image based plant identification has been the lack of quality training image data. A few attempts for solving this problem through generating high quality plant images from crowd sourced Web image collections like Flickr are proposed in this paper. These methods try to automatically identify correct and informative training images from those Web images, which typically...
This paper proposes a cascaded classifier framework for better image recognition. The proposed method is based on the confidence values given by the classifiers. By using our proposed topN-Exemplar SVM in the second stage and comparing the confidence values with those from the first stage, the classification results with less confidence are successfully updated. The validity of our algorithm has been...
We consider the feature extraction problem based on compressive sampling for supervised image classification. Inspired by recently emerged 1D compressive sampling (1DCS) and 2DPCA techniques, a novel 2D compressive sampling method, called 2DCS, using two random underdetermined projections, is proposed. 2DCS data could be effectively used for pattern representation. Moreover, original data could be...
In this paper, we propose the application of collective network of (evolutionary) binary classifiers (CNBC) to address the problems of feature/class scalability and classifier evolution, to achieve a high classification performance over full polarimetric SAR images even though the training (ground truth) data may not be entirely accurate. The CNBC basically adopts a “Divide and Conquer” type approach...
In this paper, we propose an ensemble-based approach to boost performance of Tied Factor Analysis(TFA) to overcome some of the challenges in face recognition across large pose variations. We use Adaboost. m1 to boost TFA which has shown to possess state-of-the-art face recognition performance under large pose variations. To this end, we have employed boosting as a discriminative training in the TFA...
In this paper, we propose a dynamic technique for selecting the most informative samples in classification problems as coming in two stages: the first stage conducts sample selection in batch off-line mode based on unsupervised criteria extracted from cluster partitions, the second phase proposes an active learning scheme during on-line adaptation of classifiers in non-stationary environments. This...
A new image classification method with multiple feature-based classifier (MFC) is proposed in this paper. MFC does not use the entire feature vectors extracted from the original data in a concatenated form to classify each datum, but rather uses groups of features related to each feature vector separately. In the training stage, a confusion table calculated from each local classifier that uses a specific...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.