Recursive Discriminative Subspace Learning With l1 -Norm Distance Constraint

Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation

Thanks to the advantages of the friendly annotations and the satisfactory performance, weakly-supervised semantic segmentation (WSSS) approaches have been extensively studied. Recently, the single-stage WSSS (SS-WSSS) was awakened to alleviate problems of the expensive computational costs and the complicated training procedures in multistage WSSS. However, the results of such an immature model suffer from problems of background incompleteness and object incompleteness. We empirically find that they are caused by the insufficiency of the global object context and the lack of local regional contents, respectively. Under these observations, we propose an SS-WSSS model with only the image-level class label supervisions, termed weakly supervised feature coupling network (WS-FCN), which can capture the multiscale context formed from the adjacent feature grids, and encode the fine-grained spatial information from the low-level features into the high-level ones. Specifically, a flexible context aggregation (FCA) module is proposed to capture the global object context in different granular spaces. Besides, a semantically consistent feature fusion (SF2) module is proposed in a bottom-up parameter-learnable fashion to aggregate the fine-grained local contents. Based on these two modules, WS-FCN lies in a self-supervised end-to-end training fashion. Extensive experimental results on the challenging PASCAL VOC 2012 and MS COCO 2014 demonstrate the effectiveness and efficiency of WS-FCN, which can achieve state-of-the-art results by 65.02% and 64.22% mIoU on PASCAL VOC 2012 val set and test set, 34.12% mIoU on MS COCO 2014 val set, respectively. The code and weight have been released at:WS-FCN.

Multiview Learning With Robust Double-Sided Twin SVM

Multiview learning (MVL), which enhances the learners' performance by coordinating complementarity and consistency among different views, has attracted much attention. The multiview generalized eigenvalue proximal support vector machine (MvGSVM) is a recently proposed effective binary classification method, which introduces the concept of MVL into the classical generalized eigenvalue proximal support vector machine (GEPSVM). However, this approach cannot guarantee good classification performance and robustness yet. In this article, we develop multiview robust double-sided twin SVM (MvRDTSVM) with SVM-type problems, which introduces a set of double-sided constraints into the proposed model to promote classification performance. To improve the robustness of MvRDTSVM against outliers, we take L1-norm as the distance metric. Also, a fast version of MvRDTSVM (called MvFRDTSVM) is further presented. The reformulated problems are complex, and solving them are very challenging. As one of the main contributions of this article, we design two effective iterative algorithms to optimize the proposed nonconvex problems and then conduct theoretical analysis on the algorithms. The experimental results verify the effectiveness of our proposed methods.

Learning Robust Discriminant Subspace Based on Joint L₂,ₚ- and L₂,ₛ-Norm Distance Metrics

Recently, there are many works on discriminant analysis, which promote the robustness of models against outliers by using L₁- or L_2,1-norm as the distance metric. However, both of their robustness and discriminant power are limited. In this article, we present a new robust discriminant subspace (RDS) learning method for feature extraction, with an objective function formulated in a different form. To guarantee the subspace to be robust and discriminative, we measure the within-class distances based on [Formula: see text]-norm and use [Formula: see text]-norm to measure the between-class distances. This also makes our method include rotational invariance. Since the proposed model involves both [Formula: see text]-norm maximization and [Formula: see text]-norm minimization, it is very challenging to solve. To address this problem, we present an efficient nongreedy iterative algorithm. Besides, motivated by trace ratio criterion, a mechanism of automatically balancing the contributions of different terms in our objective is found. RDS is very flexible, as it can be extended to other existing feature extraction techniques. An in-depth theoretical analysis of the algorithm's convergence is presented in this article. Experiments are conducted on several typical databases for image classification, and the promising results indicate the effectiveness of RDS.

A flexible analytic wavelet transform based approach for motor-imagery tasks classification in BCI applications

BACKGROUND AND OBJECTIVE

Motor Imagery (MI) based Brain-Computer-Interface (BCI) is a rising support system that can assist disabled people to communicate with the real world, without any external help. It serves as an alternative communication channel between the user and computer. Electroencephalogram (EEG) recordings prove to be an appropriate choice for imaging MI tasks in a BCI system as it provides a non-invasive way for completing the task. The reliability of a BCI system confides on the efficiency of the assessment of different MI tasks.

METHODS

The present work proposes a new approach for the classification of distinct MI tasks based on EEG signals using the flexible analytic wavelet transform (FAWT) technique. The FAWT decomposes the EEG signal into sub-bands and temporal moment-based features are extracted from the sub-bands. Feature normalization is applied to minimize the bias nature of classifier. The FAWT-based features are utilized as inputs to multiple classifiers. Ensemble learning method based Subspace k-Nearest Neighbour (kNN) classifier is established as the best and robust classifier for the distinction of the right hand (RH) and right foot (RF) MI tasks.

RESULTS

The sub-band (SB) wise features are tested on multiple classifiers and best performance parameters are obtained using the ensemble method based subspace kNN classifier. The best results of parameters are obtained for fourth SB as accuracy 99.33%, sensitivity 99%, specificity 99.6%, F1-Score 0.9925, and kappa value 0.9865. The other sub-bands are also attained significant results using subspace KNN classifier.

CONCLUSIONS

The proposed work explores the utility of FAWT based features for the classification of RH and RF MI tasks EEG signals. The suggested work highlights the effectiveness of multiple classifiers for classification MI-tasks. The proposed method shows better performance in comparison to state-of-arts methods. Thus, the potential to implement a BCI system for controlling wheelchairs, robotic arms, etc.

A novel event-triggered communication strategy for second-order multiagent systems

This paper concentrates on the design of an event-triggered communication strategy for secondary multi-agent systems. Many existing results in this field usually require centralized information depending on the Laplacian matrices. In a real application, however, such the constraint is conservative. To address it, this paper proposes an event-triggered sampling mechanism for interagent communication with updated thresholds. Accordingly, consensus protocols with adaptive coupling control gains are proposed for both a fixed topology and switching topologies. It is proven that the proposed method guarantees the leader-following consensus for second-order multiagent systems with an arbitrarily connected topology and even with jointly connected switching topologies. The effectiveness of the proposed scheme is verified by simulation examples.

Four-Direction Search Scheme of Path Planning for Mobile Agents

This paper presents a neural network-based four-direction search scheme of path planning for mobile agents, given a known environmental map with stationary obstacles. Firstly, the map collision energy is modeled for all the obstacles based on neural network. Secondly, for the shorted path-search purpose, the path energy is considered. Thirdly, to decrease the path-search time, a variable step-length is designed with respect to collision energy of the previous iteration path. Simulation results demonstrate that the variable step-length is effective and can decrease the iteration time substantially. Lastly, experimental results show that the mobile agent tracks the generated path well. Both the simulation and experiment results substantiate the feasibility and realizability of the presented scheme.