Automatic image annotation via compact graph based semi-supervised learning

Joint clothes image detection and search via anchor free framework

Clothes image search is an important learning task in fashion analysis to find the most relevant clothes in a database given a user-provided query. To address this problem, most existing methods employ a two-step approach, i.e., first detect the target clothes, and then crop it to feed the model for similarity learning. But the two-step approach is time-consuming and resource-intensive. On the other hand, one-step methods provide efficient solutions to integrate clothes detection and search in a unified framework. However, since one-step methods usually explore anchor-based detectors, they inevitably inherit limitations, such as high computational complexity caused by dense anchors, and high sensitivity to hyperparameters. To address the aforementioned issues, we propose an anchor-free framework for joint clothes detection and search. Specifically, we first choose an anchor-free detector as backbone. We then add a mask prediction branch and a Re-ID embedding branch to the framework. The mask prediction branch aims to predict the masks of clothes, while Re-ID embedding branch aims to extract the rich embedding features of clothes, in which we aggregate the feature of clothes via a mask pooling module by referencing the estimated target clothes masks. In this way, the extracted target clothes features can grasp more information in the area of the clothes mask; finally, we further introduce a match loss to fine-tune the embedding feature in Re-ID branch for improving the retrieval performance. Simulation results based on real datasets demonstrate the effectiveness of the proposed work.

Person re-identification via semi-supervised adaptive graph embedding

Video surveillance is an indispensable part of the smart city for public safety and security. Person Re-Identification (Re-ID), as one of elementary learning tasks for video surveillance, is to track and identify a given pedestrian in a multi-camera scene. In general, most existing methods has firstly adopted a CNN based detector to obtain the cropped pedestrian image, it then aims to learn a specific distance metric for retrieval. However, unlabeled gallery images are generally overlooked and not utilized in the training. On the other hands, Manifold Embedding (ME) has well been applied to Person Re-ID as it is good to characterize the geometry of database associated with the query data. However, ME has its limitation to be scalable to large-scale data due to the huge computational complexity for graph construction and ranking. To handle this problem, we in this paper propose a novel scalable manifold embedding approach for Person Re-ID task. The new method is to incorporate both graph weight construction and manifold regularized term in the same framework. The graph we developed is discriminative and doubly-stochastic so that the side information has been considered so that it can enhance the clustering performances. The doubly-stochastic property can also guarantee the graph is highly robust and less sensitive to the parameters. Meriting from such a graph, we then incorporate the graph construction, the subspace learning method in the unified loss term. Therefore, the subspace results can be utilized into the graph construction, and the updated graph can in turn incorporate discriminative information for graph embedding. Extensive simulations is conducted based on three benchmark Person Re-ID datasets and the results verify that the proposed method can achieve better ranking performance compared with other state-of-the-art graph-based methods.

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain-Computer Interface

In an electroencephalogram- (EEG-) based brain–computer interface (BCI), a subject can directly communicate with an electronic device using his EEG signals in a safe and convenient way. However, the sensitivity to noise/artifact and the non-stationarity of EEG signals result in high inter-subject/session variability. Therefore, each subject usually spends long and tedious calibration time in building a subject-specific classifier. To solve this problem, we review existing signal processing approaches, including transfer learning (TL), semi-supervised learning (SSL), and a combination of TL and SSL. Cross-subject TL can transfer amounts of labeled samples from different source subjects for the target subject. Moreover, Cross-session/task/device TL can reduce the calibration time of the subject for the target session, task, or device by importing the labeled samples from the source sessions, tasks, or devices. SSL simultaneously utilizes the labeled and unlabeled samples from the target subject. The combination of TL and SSL can take advantage of each other. For each kind of signal processing approaches, we introduce their concepts and representative methods. The experimental results show that TL, SSL, and their combination can obtain good classification performance by effectively utilizing the samples available. In the end, we draw a conclusion and point to research directions in the future.

Robust Graph Learning From Noisy Data

Learning graphs from data automatically have shown encouraging performance on clustering and semisupervised learning tasks. However, real data are often corrupted, which may cause the learned graph to be inexact or unreliable. In this paper, we propose a novel robust graph learning scheme to learn reliable graphs from the real-world noisy data by adaptively removing noise and errors in the raw data. We show that our proposed model can also be viewed as a robust version of manifold regularized robust principle component analysis (RPCA), where the quality of the graph plays a critical role. The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption and 2) improved graph construction by exploiting clean data recovered by RPCA. Thus, it boosts the clustering, semisupervised classification, and data recovery performance overall. Extensive experiments on image/document clustering, object recognition, image shadow removal, and video background subtraction reveal that our model outperforms the previous state-of-the-art methods.

Nonrigid Point Set Registration With Robust Transformation Learning Under Manifold Regularization

This paper solves the problem of nonrigid point set registration by designing a robust transformation learning scheme. The principle is to iteratively establish point correspondences and learn the nonrigid transformation between two given sets of points. In particular, the local feature descriptors are used to search the correspondences and some unknown outliers will be inevitably introduced. To precisely learn the underlying transformation from noisy correspondences, we cast the point set registration into a semisupervised learning problem, where a set of indicator variables is adopted to help distinguish outliers in a mixture model. To exploit the intrinsic structure of a point set, we constrain the transformation with manifold regularization which plays a role of prior knowledge. Moreover, the transformation is modeled in the reproducing kernel Hilbert space, and a sparsity-induced approximation is utilized to boost efficiency. We apply the proposed method to learning motion flows between image pairs of similar scenes for visual homing, which is a specific type of mobile robot navigation. Extensive experiments on several publicly available data sets reveal the superiority of the proposed method over state-of-the-art competitors, particularly in the context of the degenerated data.

Improved Transductive Support Vector Machine for a Small Labelled Set in Motor Imagery-Based Brain-Computer Interface

Long and tedious calibration time hinders the development of motor imagery- (MI-) based brain-computer interface (BCI). To tackle this problem, we use a limited labelled set and a relatively large unlabelled set from the same subject for training based on the transductive support vector machine (TSVM) framework. We first introduce an improved TSVM (ITSVM) method, in which a comprehensive feature of each sample consists of its common spatial patterns (CSP) feature and its geometric feature. Moreover, we use the concave-convex procedure (CCCP) to solve the optimization problem of TSVM under a new balancing constraint that can address the unknown distribution of the unlabelled set by considering various possible distributions. In addition, we propose an improved self-training TSVM (IST-TSVM) method that can iteratively perform CSP feature extraction and ITSVM classification using an expanded labelled set. Extensive experimental results on dataset IV-a from BCI competition III and dataset II-a from BCI competition IV show that our algorithms outperform the other competing algorithms, where the sizes and distributions of the labelled sets are variable. In particular, IST-TSVM provides average accuracies of 63.25% and 69.43% with the abovementioned two datasets, respectively, where only four positive labelled samples and sixteen negative labelled samples are used. Therefore, our algorithms can provide an alternative way to reduce the calibration time.

Sub-Graph Regularization on Kernel Regression for Robust Semi-Supervised Dimensionality Reduction

Dimensionality reduction has always been a major problem for handling huge dimensionality datasets. Due to the utilization of labeled data, supervised dimensionality reduction methods such as Linear Discriminant Analysis tend achieve better classification performance compared with unsupervised methods. However, supervised methods need sufficient labeled data in order to achieve satisfying results. Therefore, semi-supervised learning (SSL) methods can be a practical selection rather than utilizing labeled data. In this paper, we develop a novel SSL method by extending anchor graph regularization (AGR) for dimensionality reduction. In detail, the AGR is an accelerating semi-supervised learning method to propagate the class labels to unlabeled data. However, it cannot handle new incoming samples. We thereby improve AGR by adding kernel regression on the basic objective function of AGR. Therefore, the proposed method can not only estimate the class labels of unlabeled data but also achieve dimensionality reduction. Extensive simulations on several benchmark datasets are conducted, and the simulation results verify the effectiveness for the proposed work.

Local configuration pattern features for age-related macular degeneration characterization and classification

Age-related Macular Degeneration (AMD) is an irreversible and chronic medical condition characterized by drusen, Choroidal Neovascularization (CNV) and Geographic Atrophy (GA). AMD is one of the major causes of visual loss among elderly people. It is caused by the degeneration of cells in the macula which is responsible for central vision. AMD can be dry or wet type, however dry AMD is most common. It is classified into early, intermediate and late AMD. The early detection and treatment may help one to stop the progression of the disease. Automated AMD diagnosis may reduce the screening time of the clinicians. In this work, we have introduced LCP to characterize normal and AMD classes using fundus images. Linear Configuration Coefficients (CC) and Pattern Occurrence (PO) features are extracted from fundus images. These extracted features are ranked using p-value of the t-test and fed to various supervised classifiers viz. Decision Tree (DT), Nearest Neighbour (k-NN), Naive Bayes (NB), Probabilistic Neural Network (PNN) and Support Vector Machine (SVM) to classify normal and AMD classes. The performance of the system is evaluated using both private (Kasturba Medical Hospital, Manipal, India) and public domain datasets viz. Automated Retinal Image Analysis (ARIA) and STructured Analysis of the Retina (STARE) using ten-fold cross validation. The proposed approach yielded best performance with a highest average accuracy of 97.78%, sensitivity of 98.00% and specificity of 97.50% for STARE dataset using 22 significant features. Hence, this system can be used as an aiding tool to the clinicians during mass eye screening programs to diagnose AMD.