Label tree based image classification using sum match kernel

This paper examines the possibilities of using Landsat Thematic Mapper images for updating land-use information on topographic maps. Information obtained from satellite images can be kept up-todate and a large number of classes can be distinguished. However, the quality of the information still leaves much to be desired, with a reliability of no more than 40 - 90 %. By using digitized landuse information from a topographic map as a source of contest information the reliability could be improved considerably. The method permitted the Identification of a large number of additional classes and provided quantitative insight into the dynamics of landscap change. Verification using 1:18,000 scale aerial photographs and field data showed the results to have a reliability of over 95 %. It can be expected that whereever topographic maps permit the extraction of land-use information in a similar way as described in this paper, remote sensing information will meet operational accuracy requirements for many fields of application e.g. physical planning, map udating, land-use planning etc. Paper presented at the IGARSS'88 conference Remote Sensing - moving towards the 21st century in Edinburgh, Scotland, 12-16 September 1988

Conventional application of convolutional neural networks (CNNs) for image classification and recognition is based on the assumption that all target classes are equal (i.e. no hierarchy) and exclusive of one another (i.e. no overlap). CNN-based image classifiers built on this assumption, therefore, cannot take into account an innate hierarchy among target classes (e.g. cats and dogs in animal image classification) or additional information that can be easily derived from the data (e.g. numbers larger than five in the recognition of handwritten digits), thereby resulting in scalability issues when the number of target classes is large. Combining two related but slightly different ideas of hierarchical classification and logical learning by auxiliary inputs, we propose a new learning framework called hierarchical auxiliary learning, which not only address the scalability issues with a large number of classes but also could further reduce the classification/recognition errors with a reasonable number of classes. In the hierarchical auxiliary learning, target classes are semantically or non-semantically grouped into superclasses, which turns the original problem of mapping between an image and its target class into a new problem of mapping between a pair of an image and its superclass and the target class. To take the advantage of a superclass as a hint during the learning phase, we introduce an auxiliary block into a neural network, which generates auxiliary scores used as additional information for final classification/recognition; in this paper, we add the auxiliary block between the last residual block and the fully-connected output layer of the ResNet. Experimental results show that the proposed hierarchical auxiliary learning reduces classification errors up to 0.56, 1.6 and 3.56 percent with MNIST, SVHN and CIFAR-10 datasets, respectively.

Spectral clustering (SC) is a large family of grouping methods that partition data using eigenvectors of an affinity matrix derived from the data. Though SC methods have been successfully applied to a large number of challenging clustering scenarios, it is noteworthy that they will fail when there are significant intersections among different clusters. In this paper, based on the analysis that SC methods are able to work well when the affinity values of the points belonging to different clusters are relatively low, we propose a new method, called spectral multi-manifold clustering (SMMC), which is able to handle intersections. In our model, the data are assumed to lie on or close to multiple smooth low-dimensional manifolds, where some data manifolds are separated but some are intersecting. Then, local geometric information of the sampled data is incorporated to construct a suitable affinity matrix. Finally, spectral method is applied to this affinity matrix to group the data. Extensive experiments on synthetic as well as real datasets demonstrate the promising performance of SMMC.

High-dimensional data is usually drawn from the union of multiple low-dimensional subspaces. The task of subspace clustering is to cluster high-dimensional data into their corresponding subspace. Subspace clustering algorithm based on spectral clustering is one of the important methods of subspace clustering. This method is proposed by the spectral clustering framework. This type of method is usually divided into two steps, namely learning the affinity matrix and obtaining the segmentation matrix by spectral clustering. However, the results obtained this way are often sub-optimal. Meanwhile many state-of-the-art algorithms do not consider consistency of correlation data, resulting in the affinity matrix either too dense to make the algorithm contain a lot of erroneous information, or too sparse to make the algorithm lose correlation information. In this paper, we propose Correlation Structured Low-Rank Subspace Clustering (CSLRSC). The CSLRSC is based on the model of low rank representation by adding new $l_{1}$ norm to solve the problem that the affinity matrix established by the previous method is too dense. Adding the structured norm to the model can integrate affinity matrix learning and spectral clustering into one step to obtain an approximate optimal solution of the algorithm. The experimental results that we obtain on Extended Yale B face dataset, MINIST hand-write dataset, and ORL dataset show that our algorithm is superior to others.

The state-of-the-art object detection and image classification methods can perform impressively on more than 9k classes. In contrast, the number of classes in semantic segmentation datasets is relatively limited. This is not surprising when the restrictions caused by the lack of labeled data and high computation demand for segmentation are considered. In this paper, we propose a novel training methodology to train and scale the existing semantic segmentation models for a large number of semantic classes without increasing the memory overhead. In our embedding-based scalable segmentation approach, we reduce the space complexity of the segmentation model’s output from O(C) to O(1), propose an approximation method for ground-truth class probability, and use it to compute cross-entropy loss. The proposed approach is general and can be adopted by any state-of-the-art segmentation model to gracefully scale it for any number of semantic classes with only one GPU. Our approach achieves similar, and in some cases, even better mIoU for Cityscapes, Pascal VOC, ADE20k, COCO-Stuff10k datasets when adopted to DeeplabV3+ model with different backbones. We demonstrate a clear benefit of our approach on a dataset with 1284 classes, bootstrapped from LVIS and COCO annotations, with almost three times better mIoU than the DeeplabV3+. Our source code is available at: https://github.com/shipra25jain/ESSNet.

A learning-based classification problem with a large number of classes is considered. The error-correcting-output-codes (ЕСОС) scheme is optimized. An initial binary matrix is formed at random so that the number of its rows is equal to the number of classes and each column corresponds to the union of several classes in two macroclasses. In the ЕСОС approach, a binary classification problem is solved for every object to be recognized and for every union. The object is assigned to the class with the nearest code row. A generalization of the ЕСОС approach is presented in which a discrete optimization problem is solved to find optimal unions, probabilities of correct classification are used in dichotomy problems, and the degree of dichotomy informativeness is taken into account. If the solution algorithms for the dichotomy problems are correct, the recognition algorithm for the original problem is correct as well.

Spectral clustering has exhibited a superior performance in analyzing the cluster structure of network. However, the exponentially computational complexity limits its application in analyzing large-scale social networks. To tackle this problem, many low-rank matrix approximating algorithms are proposed, of which the NystrÖm method is an approach with proved lower approximate errors. Currently, most existing sampling techniques for NystrÖm method are designed on affinity matrices, which are time-consuming to compute by some similarity metrics. Moreover, the social networks are often built on link relations, in which there is no information to construct an affinity matrix for the approximate computing of NystrÖm method for spectral clustering except for the degrees of nodes. This paper proposes a spectral clustering algorithm for large-scale social networks via a pre-coarsening sampling based NystrÖm method. By virtue of a novel triangle-based coarsening policy, the proposed algorithm first shrinks the social network into a smaller weighted network, and then does an efficient sampling for NystrÖm method to approximate the eigen-decomposition of matrix of spectral clustering. Experimental results on real large-scale social networks demonstrate that the proposed algorithm outperforms the state-of-the-art spectral clustering algorithms, which are realized by the existing sampling techniques based NystrÖm methods.

Visual thalamic neurons were stained in a Golgilike fashion following cortical injections of horseradish peroxidase (HRP). Such staining allows neurons to be classified on the basis of their dendritic morphology, and it enables the direct relation of morphologically identified neurons with their respective cortical projection target to be visualized. All classes of neurons categorized on the basis of Golgi material (Guillery, '66) were identified in the dorsal part of the lateral geniculate body (LGBd): class 1 and class 2 neurons in the laminae A, A1, and C; class 3 neurons in laminae A and A1; class 4 cells in the C‐laminae. Three subtypes of class 4 neurons were differentiated: round cells, spindle cells, and fusiform cells. The round subtype is similar in dendritic morphology to the class 3 neurons, but its soma is larger (mean soma diameter 17 μm compared with 13 μm). Other types of neurons were identified in the laminae A, A1, and C, having morphological characteristics intermediate between class 1 and class 2, and between class 2 and class 3.Class 1 neurons, class 2 neurons, and flat neurons were identified in the medial interlaminar nucleus (MIN). The flat type is similar in morphology to the fusiform type in the C‐laminae; however, its soma is larger (mean soma diameter 23 μm compared with 19 μm), and its dendrites are free of appendages.In the extrageniculate nuclei three types of neurons were found: class 2 neurons in the pulvinar, medium‐sized cells—probably class 5—in the pulvinar and in the nucleus lateralis posterior, and neurons with an isodendritic branching pattern in the intralaminar nuclei.The cortical projections of the various thalamic cell classes were analyzed by injection of HRP into acallosal parts, or callosal parts of area 17 or area 18. Area 17 receives input from a large number of class 2 neurons and from a moderate number of class 1 neurons in the LGBd. In contrast, area 18 receives a dominant input from class 1 neurons and only weak input from class 2 neurons (up to 10% of the population of projection cells in the individual cases).Class 3 neurons in the A‐laminae and class 4 neurons in the C‐laminae project to either cortical area. Class 2 neurons in MIN project only to callosal parts of area 18, whereas class 2 neurons in pulvinar project in addition to acallosal parts of area 18. The significant change in the relative number of class 1 and class 2 neurons in the LGBd occurs gradually across the callosal zone from area 17 to area 18; it is not strictly related to the 17/18 border as defined by cytoarchitectonic or physiological criteria. The class 1/class 2 relation in the projection to area 18 is independent of eccentricity in the A‐laminae. An increase in the frequency of occurrence with eccentricity is noted, however, for class 4 neurons in the C‐laminae and for flat neurons in MIN. The correlation between neuronal function and morphology is discussed. It is concluded that, in addition to strong input with y‐characteristics, area 18 receives significant inputs with non‐y properties. latter inputs arise mainly from the laminae of the LGBd and from extra‐geniculate nuclei, but also may be seen to originate from MIN and the A‐laminae of the LGBd.

Question classification is an important phase in question answering systems. In this paper, we propose to apply i) hierarchical classifiers, ii) hierarchical classifiers in combination with semi-supervised learning and iii) hierarchy expansion for question classification for improving the precision. When the number of classes is large, the performance of classification algorithms may be affected. In order to improve the performance by reducing the number of classes for each classifier, we propose to use hierarchical classifiers according to the question taxonomy, in which each internal node is attached a classifier. We try to use semi-supervised learning to consume unlabeled questions with expectation to improve the performance of classifiers in the hierarchy. We explored different applications of learning methods in for each classifier of the hierarchy: a) supervised learning for all classifiers at all levels; b) semi-supervised learning for the first-level classifier and supervised learning for other classifiers; c) semi-supervised learning for all classifiers. The experiments show that the first method (a) has better results than those of flat classification; the second method (b) produces better results than those of the first method while the effort to increase the performance of fine classifiers in the last method (c) is not so successful. As another effort, we propose to automatically group question classes by clustering in order to expand a node which has a large number of classes in the question taxonomy. The experiment also shows that the overall precision is improved.

Evaluating the effects of similar-class combination on class integration test order generation

Classification is one of the widely used techniques to quantify and mine the rich information present in hyperspectral imagery. However, the realization of trustworthy classification still continues to be a challenging task. This is due to the presence of various uncertainties, such as incomplete a priori knowledge on the actual number of classes and noise. Especially, mismatching between the number of spectral classes and the number of information classes leads to substantial omission or commission errors in the classification. In this letter, we present a new multiclass classification framework, named supervised cascaded classifier system (SC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S), that addresses the abovementioned problem by providing reliable results. The SC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S method is a two-stage cascaded classification procedure that involves quantifying the uncertainty and then classifying the samples. In the first stage, pixels for which no reliable training samples can be found in the training stage are detected. In the second stage, pixels that are matched with the respective training distribution are classified using a supervised learning algorithm, otherwise labeled as unknown. The proposed SC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S framework has been implemented on eight different classification scenarios with a varying number of unknown classes (UCs) using hyperspectral and multispectral imageries. The performance of the proposed SC <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> S method is compared with other widely used classifiers with and without reject-option. The experimental results indicate that our method offers superior classification results even in the case of data sets with a large number of unknown spectral classes.

Simultaneously learning affinity matrix and data representations for machine fault diagnosis

Machine learning based algorithms, such as a decision tree (DT) classifier, have been applied to automated process monitoring and fault identification in manufacturing processes, however the current DT-based process control models employ a single DT classifier for both mean shift detection and fault identification. As many manufacturing processes use automated data collection for multiple process parameters, a DT classifier would have to handle a large number of classes. Previous research shows that a large number of classes can degrade the accuracy of a DT multiclass classifier. In this study we propose a new process monitoring model using multiple DT classifiers with each handling a small number of classes. Moreover, we not only detect mean shifts but also identify process variability levels that may cause out-of-control signals. Experimental results show that our proposed model achieves satisfactory performance in process monitoring and fault identification with various parameter settings. It achieves better ARL performance compared with the baseline method based on a single DT classifier.

This paper proposes a growable switch architecture with multiple modules comprising a CORE module to support highspeed switching and EDGE modules with large buffers, providing a large number of traffic classes. For open-loop traffic such as CBR and VBR, the proposed switch uses a weighted fair queueing scheduler at each EDGE buffer module based on the equivalent bandwidth allocated by the call admission control (CAC). On the other hand, for best effort class services (e.g., ABR and UBR), closed-loop control using adaptive rate control at the actual source and at the virtual source queue of the input EDGE module is proposed to avoid internal congestion and to achieve fair throughput performance among the flows competing on the same link. Simulation results show that the proposed architecture achieves ATM switches having hundreds of Gbps capacity, while providing a large number of QoS classes with high throughput and fair sharing of bandwidth by all flows.

Subspace clustering refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Current subspace clustering approaches are usually based on a two-stage framework. In the first stage, an affinity matrix is generated from data. In the second one, spectral clustering is applied on the affinity matrix. However, the affinity matrix produced by two-stage methods cannot fully reveal the similarity between data points from the same subspace, resulting in inaccurate clustering. Besides, most approaches fail to solve large-scale clustering problems due to poor efficiency. In this paper, we first propose a new scalable sparse method called Iterative Maximum Correlation (IMC) to learn the affinity matrix from data. Then we develop Piecewise Correlation Estimation (PCE) to densify the intra-subspace similarity produced by IMC. Finally we extend our work into a Sparse-Dense Subspace Clustering (SDSC) framework with a dense stage to optimize the affinity matrix for two-stage methods. We show that IMC is efficient for large-scale tasks, and PCE ensures better performance for IMC. We show the universality of our SDSC framework for current two-stage methods as well. Experiments on benchmark data sets demonstrate the effectiveness of our approaches.