Solution of instance-based recognition problems with a large number of classes

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

The label tree-based classification is one of the most popular approaches for reducing the testing complexity to sublinear with the large number of classes. One of the popular approaches to generate the label tree is to apply recursively a spectral clustering algorithm to an affinity matrix for partition set of class labels into subsets, each subset corresponds to a child node of the tree. To obtain the affinity matrix from confusion matrix, a set of N binary one-versus-all classifiers is trained and applied on validation set, where N is number of classes. However, these approaches are not reliable when there are a large number of classes because it is too costly to train these classifiers. Furthermore, the affinity matrix could not reflect the real similarity among classes due to the classification accuracy can be low. In addition, the resulting label tree may not be balanced due to the objective function of spectral clustering penalizes unbalanced partitions. In this paper, to achieve better similarity measurement between classes and without using one-versus-all classifiers, we adopt the sum match kernel to get similarity matrix. Moreover, we propose a heuristic for learning balanced tree structure by adjusting the number of class labels in clusters after the spectral clustering is done. The experimental results on benchmark datasets SUN-397 and Caltech-256 show that the performance of the proposed approach outperforms significantly the other approaches.

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.

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.

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

The technique of discriminant analysis is widely used for discriminating arson from nonarson structures. Since in this particular case only two groups are involved viz., the arson and the match groups, the computations required for obtaining a discriminant function are relatively simple. Because of this, it is possible to delete a variable by examining the value of a sub i d sub i where a sub i is the coefficient for the i-th variable in the discriminant function and d sub i is the difference between the means for the arson and the match groups for the i th variable (i=1, 2, ... , p). Thus, if a sub i d sub i is less than 0 then we delete the i th variable from consideration because inclusion of such a varable, increases the probability of misclassification. A prior knowledge of a i d i is particularly useful when we have large numbers of variables to be considered. This will help to reduce the number of discriminant functions one needs to consider in order to arrive at the discriminant function which minimizes the misclassification probability. Frequently, in developing a discriminant function one strives to increase the probability of correct classification. However, this probability reflects two components, viz., the probability of correct classification of known arson structures and the probability of correct classification of known nonarson structures. Even if the overall probability of correct classification is high, it does not necessarily imply, as the illustrations of Boston and New York City indicate, that the resulting discriminant function is also efficient in the sense that more arson cases are correctly classified than the nonarson cases. To this end, a procedure has been suggested to compute the cost of the wrong decision for a discriminant function which can be used to compare the cost of two similar types of discriminant functions. Using the relative cost efficiency criterion, it has been shown that the discriminant function for Newark is more efficient than the discriminant function for either Boston or New York City.

In this article we propose a new linear model for regression/classification of matrix input data. The algorithm for parameter estimation is constructed, some properties of the model are analyzed. The proposed model was applied for various binary classification problems, experimentally demonstrated, that in the case of small training sample, this model can be more efficient than standard techniques. In each experiment the training sample was selected randomly, the results (correct classification probabilities on the testing set) were averaged, statistical hypothesis about efficiency of the models were tested. By signed rank test most of the results are statistically significant. Bibl. 9 (in English; summaries in English, Russian and Lithuanian).

New instruments currently in design for Earth observational remote sensing from space offer promising advancements in the use of remote sensing for soil studies. Due to the enormous quantities of data generated by these high spectral resolution sensors, efficient use will only be feasible if new algorithms are developed to compress the data while maintaining information content. A spectral band selection algorithm is proposed to identify the important spectral bands for compression and classification of soil reflectance data. This algorithm was developed from the shape dominancy concept of Karhunen‐Loeve based optimal features. The high dimensional raw data were first transformed into much lower dimensionality by the derived spectral features. Canonical analysis was then used to transform the data under the maximal separability criterion into their final signal space where the data classification was performed. Soil data sets with and without stratification by soil order and climatic moisture zone were used to test the algorithm. The probabilities of correct classification of soil organic matter content using Landsat Multispectral Scanner (MSS) bands, Thematic Mapper (TM) bands, and the bands identified using the new band selection algorithm, were calculated and compared. The algorithm was successful in finding important spectral bands for soil organic matter content classification. The probabilities of correct classification obtained by using these bands were 0.850 and 0.883 for unstratified data sets, as compared to 0.600 to 0.640 for MSS bands and 0.640 to 0.653 for TM bands. Probabilities of correct classification for climate‐stratified data ranged from 0.910 to 0.980 using the calculated bands. The overall data compression ratio achieved using the algorithm was greater than 10 with no loss in classification accuracy.

Simultaneous generalized hill climbing (SGHC) algorithms provide a framework for using heuristics to simultaneously address sets of intractable discrete optimization problems where information is shared between the problems during the algorithm execution. Many well-known heuristics can be embedded within the SGHC algorithm framework. This paper shows that the solutions generated by an SGHC algorithm are a stochastic process that satisfies the Markov property. This allows problem probability mass functions to be formulated for particular sets of problems based on the long-term behavior of the algorithm. Such results can be used to determine the proportion of iterations that an SGHC algorithm will spend optimizing over each discrete optimization problem. Sufficient conditions that guarantee that the algorithm spends an equal number of iterations in each discrete optimization problem are provided. SGHC algorithms can also be formulated such that the overall performance of the algorithm is independent of the initial discrete optimization problem chosen. Sufficient conditions are obtained guaranteeing that an SGHC algorithm will visit the globally optimal solution for each discrete optimization problem. Lastly, rates of convergence for SGHC algorithms are reported that show that given a rate of convergence for the embedded GHC algorithm, the SGHC algorithm can be designed to preserve this rate.

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.

A Survey of Lagrangean Techniques for Discrete Optimization

We show that there exist infinitely many quartic number fields K with large class numbers such that K∕Q is a Galois extension whose Galois group is isomorphic to a given finite group. Cho and Kim proved that there are infinitely many totally real cyclic extensions over Q of degree 4 with large class numbers. We consider all the other cases of quartic Galois extensions.

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.