Unsupervised domain adaptive object detection (UDA-OD) aims to deploy a detector trained on source domain(s) to a new, unlabeled target domain. Carrying out mean-teacher self-training for UDA-OD poses a significant challenge, given that its success depends heavily on the quality of pseudo boxes. While many earlier researches have mainly centered on cross-domain transferability, they often neglect the rich intra- and inter-domain semantic structures. As a result, this neglect empirically restricts the discriminative abilities of the learning model. In our study, we have found a notable alignment and synergy across contrastive learning, prototype learning, and mean-teacher self-training. Building on this insight, we introduce the Prototype-oriented C ontrastive Mean Teacher (PoCoMT) for UDA-OD, a thorough and flexible framework that seamlessly integrates these three techniques to extract the most beneficial learning signals. Specifically, PoCoMT firstly generate more diverse and reliable probabilistic outputs from self-training through maximizing information entropy and maintaining semantic consistency; secondly, PoCoMT strives to reduce both intra-domain and inter-domain prototypical contrastive learning losses by elaborately designing a Prototype Alignment Network (ProtoAN) module, which fosters intra-domain feature aggregation, aligns inter-domain class structures, and reduces semantic loss between weak and strong augmentations of target domain data. Our ProtoAN can serve as a plugin module for traditional self-training frameworks to tackle the key problem of semantic loss in UDA-OD. Extensive experiments demonstrate that PoCoMT attains new state-of-the-art performance.

Unsupervised domain adaptation (UDA) plays a vital role in machine learning to tackle the homogeneous data distribution scenario. While most previous studies have concentrated on between-domain transferability, they often neglect the rich within-domain semantic structures, thus empirically narrowing the discriminative performance of the learning model. In this work, we introduce a novel approach known as prototype-oriented Class-conditional clustering transport (CLUST) for UDA. This method utilizes clustering objectives and deep prototype learning to improve UDA performance. CLUST aims to generate more diverse and reliable probabilistic outputs by maximizing informational entropy and ensuring semantic consistency. Specifically, CLUST reduces both class-conditional feature clustering transport costs and prototype clustering transport costs, fostering intra-domain feature aggregation and robust domain class structure alignment. Furthermore, CLUST maintains consistent probability predictions for same-class samples, preserving semantic structural consistency within the target data. Theoretically, we analyze the CLUST architecture concerning the target learning generalization error bound, confirming its theoretical soundness and robustness. Extensive experiments demonstrate CLUST’s effectiveness across various challenging scenarios. The experimental results show that CLUST delivers state-of-the-art or comparable performance, highlighting its robustness and practicality across diverse UDA contexts.

Domain adaptation (DA) aims to solve the problem of inconsistent distribution between training dataset and test dataset, which has attracted extensive attention. Most of the existing DA methods solve this problem by the maximum mean discrepancy (MMD) criterion or its variants. However, the noise data may lead to a significant drift of domain mean, which will reduce the performance of MMD and its variants to some extent. To this end, this paper proposes a robust domain adaptation method with possibilistic distribution distance measure. Firstly, the traditional MMD criterion is transformed into a new possibilistic clustering model, which aims to reduce the impact from noise data. This paper constructs a robust possibilistic distribution distance measure (P-DDM) criterion. It further improves the robust effectiveness of domain distribution alignment by adding the fuzzy entropy regularization term. Secondly, a domain adaptation visual classifier based on P-DDM (C-PDDM) is proposed. It adopts a graphical Laplacian matrix for preserving the geometric consistency of data in source domain and target domain. It can improve the label propagation performance. In order to improve generalization, it maximizes the use of source domain discrimination information to minimize the domain discrimination error. Theoretical analysis confirms that the proposed P-DDM is an upper bound of the traditional distribution distance measurement method MMD criterion under certain conditions. Therefore, minimizing the P-DDM can effectively optimize the MMD objective. Finally, it is compared with several representative domain adaptation methods, and the experimental results on 6 visual benchmark datasets (Office31, Office-Caltech, Office-Home, PIE, MNIST-UPS, and COIL20) show that the proposed method achieves an average improvement of about 5% on generalization performance and an average improvement of about 10% on robustness performance.

Emotion recognition holds significant potential for various real-world applications due to its reliability and precision. Nevertheless, variations in EEG patterns among individuals restrict the ability of emotion classifiers to generalize across different people. Furthermore, the non-stationary nature of EEG signals implies that a subject's data can vary over time, posing a challenge in developing models effective across multiple sessions. This paper introduces a novel domain adaptation (DA) method designed to generalize emotion recognition models across both individuals and sessions. Current mainstream DA methods primarily focus on learning discriminative domain-invariant feature (DIF) representations by integrating the "pseudo labels" of the target domain to enhance knowledge transfer. However, most approaches treat the optimization of domain-invariant features and the updating of target "pseudo labels" as two separate stages, making it challenging to achieve optimal learning performance. To address this, we propose a joint Domain-Invariant feature learning and Adaptive Graph regularized Label Propagation (DIAGLP) method for EEG-based emotion recognition. DIAGLP integrates semi-supervised knowledge adaptation and label propagation on EEG data, optimizing DIF representation and the EEG emotion recognition task within a single framework, thereby allowing mutual enhancement. Specifically, by incorporating the concept of soft labels, a domain joint distribution measurement model is established to simultaneously mitigate both marginal and conditional distribution disparities between different subjects/sessions. Additionally, an adaptive probability graph model is constructed to improve the robustness of EEG label propagation. Furthermore, a robust sigma -norm is applied to the domain joint distribution measurement and inductive learning models, creating a unified objective optimization form. Compared to several representative domain adaptation methods, the proposed method demonstrated superior or comparable performance in cross-subject and cross-session EEG emotion recognition tasks.

In order to solve the problem of inconsistent data distribution in machine learning, domain adaptation based on feature representation methods extract features from source domain, and transfer to target domain for classi cation. The existing feature representation based methods mainly solve the problem of inconsistent feature distribution between the source domain data and the target domain data, but only few methods analyze the correlation of cross-domain features between original space and shared latent space, which reduce the performance of domain adaptation. To this end, we propose a domain adaptation method with residual module, the main ideas of which are: (1) transfer the source domain data features to the target domain data through the shared latent space to achieve features sharing; (2) build a cross domain residual learning model using the latent feature space as the residual connection of the original feature space, which improves the propagation e ciency of features; (3) regular feature space to sparse features representation, which can improve the robustness of the model; and (4) give optimization algorithm, and the experiments on the public visual datasets verify the e ectiveness of the method.

As an effective machine learning paradigm, domain adaptation (DA) learning aims to enhance the learning performance of the target domain by utilizing other relevant but distinct domain(s) (referred to as the source domain(s)). The existing mainstream methods for DA mainly learn discriminative domain-invariant feature representations by combining the "pseudo labels" of the target domain to better achieve knowledge transfer. However, most existing methods alternate the optimization learning of domain-invariant features and the updating of the "pseudo labels" into two different stages, which makes them difficult to achieve optimal learning performance. In order to achieve joint optimization learning of updating the "pseudo labels" and domain-invariant feature representations, a framework of Domain-Invariant Label prOpagation (DILO) with adaptive graph regularization is proposed. By combining semi-supervised knowledge adaptation and label propagation on domain data, DILO jointly optimizes domain-invariant feature representations and target learning tasks in a unified framework, allowing these two objectives to mutually benefit. Specifically, by introducing the concept of soft labels, a joint distribution measurement model is established to simultaneously alleviate both marginal and conditional distribution differences between different domains; constructing an adaptive probability graph model to enhance the robustness of label propagation. Moreover, a robust sigma -norm is applied to domain joint distribution measurement and inductive learning models to form a unified objective optimization formulation. An effective optimization algorithm is proposed for addressing the optimization problem of DILO. Compared with several representative DA methods, the proposed method achieved better or comparable robustness in adaptation learning on four cross-domain visual datasets.

As an important branch in the field of affective computing, emotion recognition based on electroencephalography (EEG) faces a long-standing challenge due to individual diversities. To conquer this challenge, domain adaptation (DA) or domain generalization (i.e., DA without target domain in the training stage) techniques have been introduced into EEG-based emotion recognition to eliminate the distribution discrepancy between different subjects. The preceding DA or domain generalization (DG) methods mainly focus on aligning the global distribution shift between source and target domains, yet without considering the correlations between the subdomains within the source domain and the target domain of interest. Since the ignorance of the fine-grained distribution information in the source may still bind the DG expectation on EEG datasets with multimodal structures, multiple patches (or subdomains) should be reconstructed from the source domain, on which multi-classifiers could be learned collaboratively. It is expected that accurately aligning relevant subdomains by excavating multiple distribution patterns within the source domain could further boost the learning performance of DG/DA. Therefore, we propose in this work a novel DG method for EEG-based emotion recognition, i.e., Local Domain Generalization with low-rank constraint (LDG). Specifically, the source domain is firstly partitioned into multiple local domains, each of which contains only one positive sample and its positive neighbors and k2 negative neighbors. Multiple subject-invariant classifiers on different subdomains are then co-learned in a unified framework by minimizing local regression loss with low-rank regularization for considering the shared knowledge among local domains. In the inference stage, the learned local classifiers are discriminatively selected according to their importance of adaptation. Extensive experiments are conducted on two benchmark databases (DEAP and SEED) under two cross-validation evaluation protocols, i.e., cross-subject within-dataset and cross-dataset within-session. The experimental results under the 5-fold cross-validation demonstrate the superiority of the proposed method compared with several state-of-the-art methods.

The affective Brain-Computer Interface (aBCI) systems, which achieve predictions for individual subjects through training on multiple subjects, often cannot achieve satisfactory results due to the differences in Electroencephalogram (EEG) patterns between subjects. One tried to use Subject-specific classifiers, but there was a lack of sufficient labeled data. To solve this problem, Domain Adaptation (DA) has recently received widespread attention in the field of EEG-based emotion recognition. Domain adaptation (DA) learning aims to solve the problem of inconsistent distributions between training and test datasets and has received extensive attention. Most existing methods use Maximum Mean Discrepancy (MMD) or its variants to minimize the problem of domain distribution inconsistency. However, noisy data in the domain can lead to significant drift in domain means, which can affect the adaptability performance of learning methods based on MMD and its variants to some extent. Therefore, we propose a robust domain adaptation learning method with possibilistic distribution distance measure. Firstly, the traditional MMD criterion is transformed into a novel possibilistic clustering model to weaken the influence of noisy data, thereby constructing a robust possibilistic distribution distance metric (P-DDM) criterion. Then the robust effectiveness of domain distribution alignment is further improved by a fuzzy entropy regularization term. The proposed P-DDM is in theory proved which be an upper bound of the traditional distribution distance measure method MMD criterion under certain conditions. Therefore, minimizing P-DDM can effectively optimize the MMD objective. Secondly, based on the P-DDM criterion, a robust domain adaptation classifier based on P-DDM (C-PDDM) is proposed, which adopts the Laplacian matrix to preserve the geometric consistency of instances in the source domain and target domain for improving the label propagation performance. At the same time, by maximizing the use of source domain discriminative information to minimize domain discrimination error, the generalization performance of the learning model is further improved. Finally, a large number of experiments and analyses on multiple EEG datasets (i.e., SEED and SEED-IV) show that the proposed method has superior or comparable robustness performance (i.e., has increased by around 10%) in most cases.

Graph based semi-supervised learning (GSSL) has been attracting more and more attention with its intui-tiveness and good learning performance in the machine learning community. However, it is found that existing graph based semi-supervised learning method has the problem of poor robustness and sensitivity to noise and abnor-mal data by analysis. In addition, the premise for the GSSL to have good performance is that the training data and test data are independently identically distribution (IID), which leads to some limitations in practical applications. In order to solve above problems, this paper proposes a novel clustering method based on structure risk minimization model, called a multi-model adaptation method of possibilistic clustering assumption (MA-PCA), and effectively minimizes the influence from the noise and abnormal instances based on different data distributions in some reproduced kernel Hilbert space. Its main ideas are as follows: the negative impact of noise and abnormal data on the method is reduced through fuzzy entropy; considering the effective multi-model adaptive learning of training data and test data in the same distribution and different distributions, it can also obtain good performance by rela-xing the constraint of IID between training data and test data; the algorithm implementation and convergence the-orem are given. A large number of experiments and in-depth analysis on multiple real visual datasets show that the proposed method has superior or comparable robustness and generalization performance.

现如今,智能导盲器械种类繁多,而真正能够解决盲人出行痛点的导盲设备仍然寥寥无几.为此,本文设计了一款改进深度学习模型YOLO v4-Tiny的盲人智能出行眼镜.实验结果表明,相比于市面上其他导盲产品,本产品相较于市面上其他避障产品更具有可靠性和适用性.

In practical encephalogram (EEG)-based machine learning, different subjects can be represented by many different EEG patterns, which would, in some extent, degrade the performance of extant subject-independent classifiers obtained from cross-subjects datasets. To this end, in this paper, we present a robust Latent Multi-source Adaptation (LMA) framework for cross-subject/dataset emotion recognition with EEG signals by uncovering multiple domain-invariant latent subspaces. Specifically, by jointly aligning the statistical and semantic distribution discrepancies between each source and target pair, multiple domain-invariant classifiers can be trained collaboratively in a unified framework. This framework can fully utilize the correlated knowledge among multiple sources with a novel low-rank regularization term. Comprehensive experiments on DEAP and SEED datasets demonstrate the superior or comparable performance of LMA with the state of the art in the EEG-based emotion recognition.

In machine learning community, graph-based semi-supervised learning (GSSL) approaches have attracted more extensive research due to their elegant mathematical formulation and good performance. However, one of the reasons affecting the performance of the GSSL method is that the training data and test data need to be independently identically distributed (IID); any individual user may show a completely different encephalogram (EEG) data in the same situation. The EEG data may be non-IID. In addition, noise/outlier sensitiveness still exist in GSSL approaches. To these ends, we propose in this paper a novel clustering method based on structure risk minimization model, called multi-model adaptation learning with possibilistic clustering assumption for EEG-based emotion recognition (MA-PCA). It can effectively minimize the influence from the noise/outlier samples based on different EEG-based data distribution in some reproduced kernel Hilbert space. Our main ideas are as follows: (1) reducing the negative impact of noise/outlier patterns through fuzzy entropy regularization, (2) considering the training data and test data are IID and non-IID to obtain a better performance by multi-model adaptation learning, and (3) the algorithm implementation and convergence theorem are also given. A large number of experiments and deep analysis on real DEAP datasets and SEED datasets was carried out. The results show that the MA-PCA method has superior or comparable robustness and generalization performance to EEG-based emotion recognition.

基于龙芯处理器的体系结构和指令系统,提出代码级和指令级优化方案,提升龙芯系列计算机的图像编码和解码速度.分析Libjpeg编解码算法的并行特性,重复使用龙芯处理器的SIMD加速硬件资源进行数据级并行优化.实验结果表明,JPEG编码速率提高70％左右,解码速率提高200％以上.工作成果已经提交到Lib-jpeg-turbo的主分支,极大改善了国产龙芯系列计算机中多媒体相关应用的用户体验.

为了降低因疲劳作业诱发的各类安全风险,开发一套高性能的疲劳检测预警系统是十分必要的.本文设计并开发了一套基于面部识别的疲劳状态检测系统,利用Dlib官方预训练的人脸特征位置检测器获取被监测人员面部68个特征点及坐标,通过坐标计算得到的眼睛、嘴巴纵横比以捕获眨眼、打哈欠动作;同时,通过头部姿态估计算法捕获瞌睡点头动作.最终系统根据眨眼、哈欠及点头的频率综合判断被监测人员是否处于疲劳状态并作出安全提示.实验的结果表明,该疲劳状态检测系统能实时、准确地检测被监测人员的疲劳状态,并及时发出警报.

Since each individual subject may present completely different encephalogram (EEG) patterns with respect to other subjects, existing subject-independent emotion classifiers trained on data sampled from cross-subjects or cross-dataset generally fail to achieve sound accuracy. In this scenario, the domain adaptation technique could be employed to address this problem, which has recently got extensive attention due to its effectiveness on cross-distribution learning. Focusing on cross-subject or cross-dataset automated emotion recognition with EEG features, we propose in this article a robust multi-source co-adaptation framework by mining diverse correlation information (MACI) among domains and features with l2,1−norm as well as correlation metric regularization. Specifically, by minimizing the statistical and semantic distribution differences between source and target domains, multiple subject-invariant classifiers can be learned together in a joint framework, which can make MACI use relevant knowledge from multiple sources by exploiting the developed correlation metric function. Comprehensive experimental evidence on DEAP and SEED datasets verifies the better performance of MACI in EEG-based emotion recognition.

Bacterial foraging algorithm comes from the best survival selection mechanism of animals in nature. As the representative of the heuristic algorithm, the bacterial foraging algorithm has unique advantages in solving the multi difficulty scheduling problem effectively. In order to realize the artificial intelligent management of the enterprise’s staff scheduling, this paper constructs the knowledge staff scheduling model by using a bacterial foraging algorithm and analyzes the implementation principle, advantages, and disadvantages of the algorithm. The influence of the basic parameters in the algorithm model on the algorithm performance is analyzed. In order to optimize the unconventional foraging strategy, the improvement measures of bacterial foraging behavior were proposed. Finally, the performance of the optimized bacterial foraging algorithm is tested and compared with the basic bacterial foraging algorithm, genetic algorithm, and particle swarm optimization algorithm. The experimental results show that the optimized bacterial foraging algorithm can achieve better convergence accuracy and shorter convergence speed for the objective function, and it can solve the scheduling optimization problem of knowledge workers more quickly, accurately, and effectively. The research in this paper shows that the optimization of four aspects of the basic bacterial foraging algorithm improves the performance of the algorithm and provides a theoretical reference for the optimization of the bacterial foraging algorithm.

The purpose of the latest brain computer interface is to perform accurate emotion recognition through the customization of their recognizers to each subject. In the field of machine learning, graph-based semi-supervised learning (GSSL) has attracted more and more attention due to its intuitive and good learning performance for emotion recognition. However, the existing GSSL methods are sensitive or not robust enough to noise or outlier electroencephalogram (EEG)-based data since each individual subject may present noise or outlier EEG patterns in the same scenario. To address the problem, in this paper, we invent a Possibilistic Clustering-Promoting semi-supervised learning method for EEG-based Emotion Recognition. Specifically, it constrains each instance to have the same label membership value with its local weighted mean to improve the reliability of the recognition method. In addition, a regularization term about fuzzy entropy is introduced into the objective function, and the generalization ability of membership function is enhanced by increasing the amount of sample discrimination information, which improves the robustness of the method to noise and the outlier. A large number of experimental results on the three real datasets (i.e., DEAP, SEED, and SEED-IV) show that the proposed method improves the reliability and robustness of the EEG-based emotion recognition.

While multi-source adaptation has recently received much attention due to its effectiveness, limited effort has been made on improving its performance by leveraging some shared knowledge among sources and features. To this end, we propose in this paper a robust Multi-source co-Adaptation framework by mining diverse Correlation Information (MACI) among domains as well as features via joint adaptive σ-norm and correlation metric regularization. Concretely, multiple domain-invariant classification functions for different source adaptation objects are co-learned in a joint framework by minimizing both statistical and semantic distribution discrepancy between source and target domains, which enables MACI to utilize the correlated knowledge among multiple sources by exploiting the developed correlation metric function. Under this framework, MACI can preserve the original geometrical structure information as well as be robust to some noises or outliers existed in domains by employing local graph Laplacian and adaptive regression scheme. Furthermore, we also extend MACI to domain generalization scenario when the target domain of interest is unavailable in the training stage. An efficient iterative algorithm is proposed to optimize MACI (also applied to its domain generalization version), whose convergence is theoretically guaranteed. Comprehensive experimental evidence on a large number of visual datasets verifies the effectiveness of the proposed framework.

对于现有的多源自适应学习方案无法有效区分多个源域中的有用信息并迁移至目标域的问题,提出一种具有特征选择的多源自适应分类框架(MACFFS),并将特征选择和共享特征子空间学习整合到统一框架中进行联合特征学习.具体来说,MACFFS将来自多个源域的特征数据投影至不同的潜在空间中来学习得到多个源域分类模型,实现目标域的分类.然后,将得到的多个分类结果进行整合用于目标域分类模型的学习.此外,框架还利用L2,1范数稀疏回归代替传统的基于L2范数的最小二乘回归来提高鲁棒性.最后,把多种现有方法在两项任务中与MACFFS进行实验比较分析.实验结果表明,与现有方法中表现最好的DSM相比,MACFFS节省了接近1/4的计算时间,并且提升了大约2％的识别率.总的来说,MACFFS结合了机器学习、统计学习等相关知识,为多源自适应方法提供了一个新的思路,且该方法在现实场景下的识别应用中比现有方法具有更好的性能.

在机器学习领域,基于图的半监督学习凭借其直观性和良好的学习性能而吸引了越来越多的关注.针对现有的基于图的半监督学习方法对噪声和异常数据的鲁棒性不够好/较敏感的问题,提出一种基于可能性聚类假设的半监督分类方法(Semi-Supervised Classification Method of Possibilistic Clustering Assumption,SSPCA),其约束每个数据点与其局部加权均值具有相同的标签隶属度值,以此来提高分类方法的可靠性,此外,在目标函数中引入一个关于模糊熵的正则项,通过增大样本判别信息量来增强隶属度函数的泛化能力,提高了该方法对噪声和异常数据的鲁棒性.在实际数据集上的大量实验结果证实了所提方法具有很好的分类可靠性和鲁棒性.