1,721,335 research outputs found
A spin glass model of a Markov random field
No full textThis paper presents a novel algorithm for robust object recognition. We propose to model the visual appearance of objects via probability density functions. The algorithm consists of a fully connected Markov random field with energy function derived from results of statistical physics of spin glasses. Markov random fields and spin glass energy functions are combined together via nonlinear kernel functions; we call the model Spin Glass-Markov Random Field. Full connectivity enables to take into account the global appearance of the object, and its specific local characteristics at the same time, resulting in robustness to noise, occlusions, and cluttered background. We show with theoretical analysis and experiments that this new model is competitive with state-of-the-art algorithms
How to combine color and shape information for 3D object recognition: kernels do the trick
No full textThis paper presents a kernel method that allows to combine color and shape information for appearance-based object recognition. It doesn't require to define a new common representation, but use the power of kernels to combine different representations together in an effective manner. These results are achieved using results of statistical mechanics of spin glasses combined with Markov random fields via kernel functions. Experiments show an increase in recognition rate up to 5.92% with respect to conventional strategies
To each according to its need: kernel class specific classifier
No full textWe present in this paper a new multi-class Bayes classifier that permits using separate feature vectors, chosen specifically for each class. This technique extends previous work on feature Class Specific Classifier to kernel methods, using a new class of Gibbs probability distributions with nonlinear kernel mapping as energy function. The resulting method, that we call Kernel Class Specific Classifier, permits using a different kernel and a different feature set for each class. Moreover, the proper kernel for each class can be learned by the training data with a leave-one-out technique. This removes the ambiguity regarding the proper choice of the feature vectors for a given class. Experiments on appearance-based object recognition show the power of the proposed approach
The projectron: A bounded kernel-based perceptron
No full textWe present a discriminative online algorithm with a bounded memory growth, which is based on the kernel-based Perception. Generally, the required memory of the kernel-based Perceptron for storing the online hypothesis is not bounded. Previous work has been focused on discarding part of the instances in order to keep the memory bounded. In the proposed algorithm the instances are not discarded, but projected onto the space spanned by the previous online hypothesis. We derive a relative mistake bound and compare our algorithm both analytically and empirically to the state-of-the-art Forgetron algorithm (Dekel et al, 2007). The first variant of our algorithm, called Projectron, outperforms the Forgetron. The second variant, called Projectron++, outperforms even the Perceptron. Copyright 2008 by the author(s)/owner(s)
Cue integration through discriminative accumulation
No full textObject recognition systems aiming to work in real world settings should use multiple cues in order to achieve robustness. We present a new cue integration scheme which extends the idea of cue accumulation to discriminative classifiers. We derive and test the scheme for Support Vector Machines (SVMs), but we also show that it is easily extendible to any large margin classifier. Interestingly, in the case of one-class SVMs, the scheme can be interpreted as a new class of Mercer kernels for multiple cues. Experimental comparison with a probabilistic accumulation scheme is favorable to our method. Comparison with voting scheme shows that our method may suffer as the number of object classes increases. Based on these results, we propose a recognition algorithm consisting of a decision tree where decisions at each node are taken using our accumulation scheme. Results obtained using this new algorithm compare very favorably to accumulation (both probabilistic and discriminative) and voting scheme
Towards a quantitative measure of rareness
Full text linkWithin the context of detection of incongruent events, an often overlooked aspect is how a system should react to the detection. The set of all the possible actions is certainly conditioned by the task at hand, and by the embodiment of the artificial cognitive system under consideration. Still, we argue that a desirable action that does not depend from these factors is to update the internal model and learn the new detected event. This paper proposes a recent transfer learning algorithm as the way to address this issue. A notable feature of the proposed model is its capability to learn from small samples, even a single one. This is very desirable in this context, as we cannot expect to have too many samples to learn from, given the very nature of incongruent events. We also show that one of the internal parameters of the algorithm makes it possible to quantitatively measure incongruence of detected events. Experiments on two different datasets support our claim
Frustratingly easy NBNN domain adaptation
No full textOver the last years, several authors have signaled that state of the art categorization methods fail to perform well when trained and tested on data from different databases. The general consensus in the literature is that this issue, known as domain adaptation and/or dataset bias, is due to a distribution mismatch between data collections. Methods addressing it go from max-margin classifiers to learning how to modify the features and obtain a more robust representation. The large majority of these works use BOW feature descriptors, and learning methods based on image-to-image distance functions. Following the seminal work of [6], in this paper we challenge these two assumptions. We experimentally show that using the NBNN classifier over existing domain adaptation databases achieves always very strong performances. We build on this result, and present an NBNN-based domain adaptation algorithm that learns iteratively a class metric while inducing, for each sample, a large margin separation among classes. To the best of our knowledge, this is the first work casting the domain adaptation problem within the NBNN framework. Experiments show that our method achieves the state of the art, both in the unsupervised and semi-supervised settings. © 2013 IEEE
Discriminative cue integration for medical image annotation
No full textThis paper presents the algorithms and results of our participation to the image annotation task of ImageCLEFmed 2007. We proposed a multi-cue approach where images are represented both by global and local descriptors. These cues are combined following two SVM-based strategies. The first algorithm, called Discriminative Accumulation Scheme (DAS), trains an SVM for each feature, and considers as output of each classifier the distance from the separating hyperplane. The final decision is taken on a linear combination of these distances. The second algorithm, that we call Multi Cue Kernel (MCK), uses a new Mercer kernel which can accept as input different features while keeping them separated. The DAS algorithm obtained a score of 29.9, which ranked fifth among all submissions. The MCK algorithm with the one-vs-all and with the one-vs-one multiclass extensions of SVM scored respectively 26.85 and 27.54. These runs ranked first and second among all submissions. © 2008 Springer-Verlag Berlin Heidelberg
Learning categories from few examples with multi model knowledge transfer
Full text linkLearning a visual object category from few samples is a compelling and challenging problem. In several real-world applications collecting many annotated data is costly and not always possible. However a small training set does not allow to cover the high intraclass variability typical of visual objects. In this condition, machine learning methods provide very few guarantees. This paper presents a discriminative model adaptation algorithm able to proficiently learn a target object with few examples by relying on other previously learned source categories. The proposed method autonomously chooses from where and how much to transfer information by solving a convex optimization problem which ensures to have the minimal leave-one-out error on the available training set. We analyze several properties of the described approach and perform an extensive experimental comparison with other existing transfer solutions, consistently showing the value of our algorithm.LIDIA
- …
