Collaborative image retrieval via regularized metric learning

In content-based image retrieval (CBIR), relevant images are identified based on their similarities to query images. Most CBIR algorithms are hindered by the semantic gap between the low-level image features used for computing image similarity and the high-level semantic concepts conveyed in images. One way to reduce the semantic gap is to utilize the log data of users' feedback that has been collected by CBIR systems in history, which is also called “collaborative image retrieval.” In this paper, we present a novel metric learning approach, named “regularized metric learning,” for collaborative image retrieval, which learns a distance metric by exploring the correlation between low-level image features and the log data of users' relevance judgments. Compared to the previous research, a regularization mechanism is used in our algorithm to effectively prevent overfitting. Meanwhile, we formulate the proposed learning algorithm into a semidefinite programming problem, which can be solved very efficiently by existing software packages and is scalable to the size of log data. An extensive set of experiments has been conducted to show that the new algorithm can substantially improve the retrieval accuracy of a baseline CBIR system using Euclidean distance metric, even with a modest amount of log data. The experiment also indicates that the new algorithm is more effective and more efficient than two alternative algorithms, which exploit log data for image retrieval.     

Visual tracking via online discriminative multiple instance metric learning

Motion object tracking is an important issue in computer vision. In this paper, a robust tracking algorithm based on multiple instance learning (MIL) is proposed. First, a coarse-to-fine search method is designed to reduce the computation load of cropping candidate samples for a new arriving frame. Then, a bag-level similarity metric is proposed to select the most correct positive instances to form the positive bag. The instance’s importance to bag probability is determined by their Mahalanobis distance. Furthermore, an online discriminative classifier selection method, which exploits the average gradient and average weak classifiers strategy to optimize the margin function between positive and negative bags, is presented to solve the suboptimal problem in the process of selecting weak classifiers. Experimental results on challenging sequences show that the proposed method is superior to other compared methods in terms of both qualitative and quantitative assessments.     

Online classifier adaptation for cost-sensitive learning

In this paper, we propose the problem of online cost-sensitive classifier adaptation and the first algorithm to solve it. We assume that we have a base classifier for a cost-sensitive classification problem, but it is trained with respect to a cost setting different to the desired one. Moreover, we also have some training data samples streaming to the algorithm one by one. The problem is to adapt the given base classifier to the desired cost setting using the steaming training samples online. To solve this problem, we propose to learn a new classifier by adding an adaptation function to the base classifier, and update the adaptation function parameter according to the streaming data samples. Given an input data sample and the cost of misclassifying it, we update the adaptation function parameter by minimizing cost-weighted hinge loss and respecting previous learned parameter simultaneously. The proposed algorithm is compared to both online and off-line cost-sensitive algorithms on two cost-sensitive classification problems, and the experiments show that it not only outperforms them on classification performances, but also requires significantly less running time.

     

A direct boosting algorithm for the k-nearest neighbor classifier via local warping of the distance metric

Though the k-nearest neighbor (k-NN) pattern classifier is an effective learning algorithm, it can result in large model sizes. To compensate, a number of variant algorithms have been developed that condense the model size of the k-NN classifier at the expense of accuracy. To increase the accuracy of these condensed models, we present a direct boosting algorithm for the k-NN classifier that creates an ensemble of models with locally modified distance weighting. An empirical study conducted on 10 standard databases from the UCI repository shows that this new Boosted k-NN algorithm has increased generalization accuracy in the majority of the datasets and never performs worse than standard k-NN.     

Action prediction via deep residual feature learning and weighted loss

Multimedia Tools and Applications - Action prediction based on partially observed videos is challenging as the information provided by partial videos is not discriminative enough for...     

Prototype-based classifier learning for long-tailed visual recognition

Science China Information Sciences -     

Cross-datasets facial expression recognition via distance metric learning and teacher-student model

Multimedia Tools and Applications - Large-scale high-quality datasets are a particularly important condition for facial expression recognition(FER) in the era of deep learning, but most of the...     

Rough-fuzzy weighted k-nearest leader classifier for large data sets

A leaders set which is derived using the leaders clustering method can be used in place of a large training set to reduce the computational burden of a classifier. Recently, a fast and efficient leader-based classifier called weighted k-nearest leader-based classifier is shown by us to be an efficient and faster classifier. But, there exist some uncertainty while calculating the relative importance (weight) of the prototypes. This paper proposes a generalization over the earlier proposed k-nearest leader-based classifier where a novel soft computing approach is used to resolve the uncertainty. Combined principles of rough set theory and fuzzy set theory are used to analyze the proposed method. The proposed method called rough-fuzzy weighted k-nearest leader classifier (RF-wk-NLC) uses a two level hierarchy of prototypes along with their relative importance. RF-wk-NLC is shown by using some standard data sets to have improved performance and is compared with the earlier related methods.     

Evaluation of a machine learning classifier for metamodels

Modeling is a ubiquitous activity in the process of software development. In recent years, such an activity has reached a high degree of intricacy, guided by the heterogeneity of the components, data sources, and tasks. The democratized use of models has led to the necessity for suitable machinery for mining modeling repositories. Among others, the classification of metamodels into independent categories facilitates personalized searches by boosting the visibility of metamodels. Nevertheless, the manual classification of metamodels is not only a tedious but also an error-prone task. According to our observation, misclassification is the norm which leads to a reduction in reachability as well as reusability of metamodels. Handling such complexity requires suitable tooling to leverage raw data into practical knowledge that can help modelers with their daily tasks. In our previous work, we proposed AURORA as a machine learning classifier for metamodel repositories. In this paper, we present a thorough evaluation of the system by taking into consideration different settings as well as evaluation metrics. More importantly, we improve the original AURORA tool by changing its internal design. Experimental results demonstrate that the proposed amendment is beneficial to the classification of metamodels. We also compared our approach with two baseline algorithms, namely gradient boosted decision tree and support vector machines. Eventually, we see that AURORA outperforms the baselines with respect to various quality metrics.

     

Sparse semantic metric learning for image retrieval

Typical content-based image retrieval solutions usually cannot achieve satisfactory performance due to the semantic gap challenge. With the popularity of social media applications, large amounts of social images associated with user tagging information are available, which can be leveraged to boost image retrieval. In this paper, we propose a sparse semantic metric learning (SSML) algorithm by discovering knowledge from these social media resources, and apply the learned metric to search relevant images for users. Different from the traditional metric learning approaches that use similar or dissimilar constraints over a homogeneous visual space, the proposed method exploits heterogeneous information from two views of images and formulates the learning problem with the following principles. The semantic structure in the text space is expected to be preserved for the transformed space. To prevent overfitting the noisy, incomplete, or subjective tagging information of images, we expect that the mapping space by the learned metric does not deviate from the original visual space. In addition, the metric is straightforward constrained to be row-wise sparse with the ?_2,1-norm to suppress certain noisy or redundant visual feature dimensions. We present an iterative algorithm with proved convergence to solve the optimization problem. With the learned metric for image retrieval, we conduct extensive experiments on a real-world dataset and validate the effectiveness of our approach compared with other related work.     

Full-scaled deep metric learning for pedestrian re-identification

Multimedia Tools and Applications - The pedestrian re-identification problem (i.e., re-id) is essential and pre-requisite in multi-camera video surveillance studies, provided the fact that...     

Distance metric learning for graph structured data

Machine Learning - Graphs are versatile tools for representing structured data. As a result, a variety of machine learning methods have been studied for graph data analysis. Although many such...     

Dynamic probability estimator for machine learning

An efficient algorithm for dynamic estimation of probabilities without division on unlimited number of input data is presented. The method estimates probabilities of the sampled data from the raw sample count, while keeping the total count value constant. Accuracy of the estimate depends on the counter size, rather than on the total number of data points. Estimator follows variations of the incoming data probability within a fixed window size, without explicit implementation of the windowing technique. Total design area is very small and all probabilities are estimated concurrently. Dynamic probability estimator was implemented using a programmable gate array from Xilinx. The performance of this implementation is evaluated in terms of the area efficiency and execution time. This method is suitable for the highly integrated design of artificial neural networks where a large number of dynamic probability estimators can work concurrently.     

A learning classifier system for mazes with aliasing clones

Maze problems represent a simplified virtual model of the real environment and can be used for developing core algorithms of many real-world application related to the problem of navigation. Learning Classifier Systems (LCS) are the most widely used class of algorithms for reinforcement learning in mazes. However, LCSs best achievements in maze problems are still mostly bounded to non-aliasing environments, while LCS complexity seems to obstruct a proper analysis of the reasons for failure. Moreover, there is a lack of knowledge of what makes a maze problem hard to solve by a learning agent. To overcome this restriction we try to improve our understanding of the nature and structure of maze environments. In this paper we describe a new LCS agent that has a simpler and more transparent performance mechanism. We use the structure of a predictive LCS model, strip out the evolutionary mechanism, simplify the reinforcement learning procedure and equip the agent with the ability to Associative Perception, adopted from psychology. We then assess the new LCS with Associative Perception on an extensive set of mazes and analyse the results to discover which features of the environments play the most significant role in the learning process. We identify a particularly hard feature for learning in mazes, aliasing clones, which arise when groups of aliasing cells occur in similar patterns in different parts of the maze. We discuss the impact of aliasing clones and other types of aliasing on learning algorithms.     

Non-iterative online sequential learning strategy for autoencoder and classifier

Neural Computing and Applications - Artificial neural network training algorithms aim to optimize the network parameters regarding the pre-defined cost function. Gradient-based artificial neural...     

Generalized iterative RELIEF for supervised distance metric learning

The RELIEF algorithm is a popular approach for feature weighting. Many extensions of the RELIEF algorithm are developed, and I-RELIEF is one of the famous extensions. In this paper, I-RELIEF is generalized for supervised distance metric learning to yield a Mahananobis distance function. The proposed approach is justified by showing that the objective function of the generalized I-RELIEF is closely related to the expected leave-one-out nearest-neighbor classification rate. In addition, the relationships among the generalized I-RELIEF, the neighbourhood components analysis, and graph embedding are also pointed out. Experimental results on various data sets all demonstrate the superiority of the proposed approach.     

Third-order moment spectrum and weighted fuzzy classifier for robust 2-D object recognition

In this paper, a robust position, scale, and rotation invariant system for the recognition of closed 2-D noise corrupted images using the bispectral features of a contour sequence and the weighted fuzzy classifier are derived. The higher-order spectrum based on third-order moment, called a bispectrum, is applied to the contour sequences of an image to extract a 15-dimensional feature vector for each of the 2-D images. This bispectral feature vector, which is invariant to shape translation, scale, and rotation transformation, can be used to represent a 2-D planar image and is fed into a weighted fuzzy classifier for the recognition process. The experiments with eight different shapes of aircraft images are presented to illustrate the high performance of the proposed system even when the image is significantly corrupted by noise.     

Similarity learning for texture image retrieval using multiple classifier system

Multiple Classifier System has found its applications in many areas such as handwriting recognition, speaker recognition, medical diagnosis, fingerprint recognition, personal identification and others. However, there have been rare attempts to develop content-based image retrieval (CBIR) system that uses multiple classifiers to learn visual similarity. Texture as a primitive visual content is often used in many important applications (viz. Medical image analysis and medical CBIR system). In this paper, a texture image retrieval system is developed that learns the visual similarity in terms of class membership using multiple classifiers. The way proposed approach combines the decisions of multiple classifiers to obtain final class memberships of query for each of the output classes is also a novel concept. A modified distance that is weighted with the membership values obtained through similarity learning is used for ranking. Three different algorithms are proposed for the retrieval of images against a query image displaying the strength of multiple classifier approach, class membership score and their interplay to achieve the objective defined in terms of simplicity, retrieval effectiveness and speed. The proposed methods based on multiple classifiers achieve higher retrieval accuracy with lower standard deviation compared to all the competing methods irrespective of the texture database and feature set used. The multiple classifier retrieval schemes proposed here is tested for texture image retrieval. However, these can be used for any other challenging retrieval problems.