In Unsupervised Domain Adaptation(UDA)for person re-identification(re-ID),the primary challenge is reducing the distribution discrepancy between the source and target domains.This can be achieved by implicitly or expl...In Unsupervised Domain Adaptation(UDA)for person re-identification(re-ID),the primary challenge is reducing the distribution discrepancy between the source and target domains.This can be achieved by implicitly or explicitly constructing an appropriate intermediate domain to enhance recognition capability on the target domain.Implicit construction is difficult due to the absence of intermediate state supervision,making smooth knowledge transfer from the source to the target domain a challenge.To explicitly construct the most suitable intermediate domain for the model to gradually adapt to the feature distribution changes from the source to the target domain,we propose the Minimal Transfer Cost Framework(MTCF).MTCF considers all scenarios of the intermediate domain during the transfer process,ensuring smoother and more efficient domain alignment.Our framework mainly includes threemodules:Intermediate Domain Generator(IDG),Cross-domain Feature Constraint Module(CFCM),and Residual Channel Space Module(RCSM).First,the IDG Module is introduced to generate all possible intermediate domains,ensuring a smooth transition of knowledge fromthe source to the target domain.To reduce the cross-domain feature distribution discrepancy,we propose the CFCM Module,which quantifies the difficulty of knowledge transfer and ensures the diversity of intermediate domain features and their semantic relevance,achieving alignment between the source and target domains by incorporating mutual information and maximum mean discrepancy.We also design the RCSM,which utilizes attention mechanism to enhance the model’s focus on personnel features in low-resolution images,improving the accuracy and efficiency of person re-ID.Our proposed method outperforms existing technologies in all common UDA re-ID tasks and improves the Mean Average Precision(mAP)by 2.3%in the Market to Duke task compared to the state-of-the-art(SOTA)methods.展开更多
:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project...:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project and the target project,which prevents the prediction model from performing well.Most existing methods overlook the class discrimination of the learned features.Seeking an effective transferable model from the source project to the target project for CPDP is challenging.In this paper,we propose an unsupervised domain adaptation based on the discriminative subspace learning(DSL)approach for CPDP.DSL treats the data from two projects as being from two domains and maps the data into a common feature space.It employs crossdomain alignment with discriminative information from different projects to reduce the distribution difference of the data between different projects and incorporates the class discriminative information.Specifically,DSL first utilizes subspace learning based domain adaptation to reduce the distribution gap of data between different projects.Then,it makes full use of the class label information of the source project and transfers the discrimination ability of the source project to the target project in the common space.Comprehensive experiments on five projects verify that DSL can build an effective prediction model and improve the performance over the related competing methods by at least 7.10%and 11.08%in terms of G-measure and AUC.展开更多
Domain shift is when the data used in training does not match the ones it will be applied to later on under similar conditions.Domain shift will reduce accuracy in results.To prevent this,domain adaptation is done,whi...Domain shift is when the data used in training does not match the ones it will be applied to later on under similar conditions.Domain shift will reduce accuracy in results.To prevent this,domain adaptation is done,which adapts the pre-trained model to the target domain.In real scenarios,the availability of labels for target data is rare thus resulting in unsupervised domain adaptation.Herein,we propose an innovative approach where source-free domain adaptation models and Generative Adversarial Networks(GANs)are integrated to improve the performance of computer vision or robotic vision-based systems in our study.Cosine Generative Adversarial Network(CosGAN)is developed as a GAN that uses cosine embedding loss to handle issues associated with unsupervised source-relax domain adaptations.For less complex architecture,the CosGAN training process has two steps that produce results almost comparable to other state-of-the-art techniques.The efficiency of CosGAN was compared by conducting experiments using benchmarked datasets.The approach was evaluated on different datasets and experimental results show superiority over existing state-of-the-art methods in terms of accuracy as well as generalization ability.This technique has numerous applications including wheeled robots,autonomous vehicles,warehouse automation,and all image-processing-based automation tasks so it can reshape the field of robotic vision with its ability to make robots adapt to new tasks and environments efficiently without requiring additional labeled data.It lays the groundwork for future expansions in robotic vision and applications.Although GAN provides a variety of outstanding features,it also increases the risk of instability and over-fitting of the training data thus making the data difficult to converge.展开更多
Labeled data scarcity of an interested domain is often a serious problem in machine learning.Leveraging the labeled data from other semantic-related yet co-variate shifted source domain to facilitate the interested do...Labeled data scarcity of an interested domain is often a serious problem in machine learning.Leveraging the labeled data from other semantic-related yet co-variate shifted source domain to facilitate the interested domain is a consensus.In order to solve the domain shift between domains and reduce the learning ambiguity,unsupervised domain adaptation(UDA)greatly promotes the transferability of model parameters.However,the dilemma of over-fitting(negative transfer)and under-fitting(under-adaptation)is always an overlooked challenge and potential risk.In this paper,we rethink the shallow learning paradigm and this intractable over/under-fitting problem,and propose a safer UDA model,coined as Bilateral Co-Transfer(BCT),which is essentially beyond previous well-known unilateral transfer.With bilateral co-transfer between domains,the risk of over/under-fitting is therefore largely reduced.Technically,the proposed BCT is a symmetrical structure,with joint distribution discrepancy(JDD)modeled for domain alignment and category discrimination.Specifically,a symmetrical bilateral transfer(SBT)loss between source and target domains is proposed under the philosophy of mutual checks and balances.First,each target sample is represented by source samples with low-rankness constraint in a common subspace,such that the most informative and transferable source data can be used to alleviate negative transfer.Second,each source sample is symmetrically and sparsely represented by target samples,such that the most reliable target samples can be exploited to tackle underadaptation.Experiments on various benchmarks show that our BCT outperforms many previous outstanding work.展开更多
Unsupervised transfer subspace learning is one of the challenging and important topics in domain adaptation,which aims to classify unlabeled target data by using source domain information.The traditional transfer subs...Unsupervised transfer subspace learning is one of the challenging and important topics in domain adaptation,which aims to classify unlabeled target data by using source domain information.The traditional transfer subspace learning methods often impose low-rank constraints,i.e.,trace norm,to preserve data structural information of different domains.However,trace norm is only the convex surrogate to approximate the ideal low-rank constraints and may make their solutions seriously deviate from the original optimums.In addition,the traditional methods directly use the strict labels of source domain,which is difficult to deal with label noise.To solve these problems,we propose a novel nonconvex and discriminative transfer subspace learning method named NDTSL by incorporating Schatten-norm and soft label matrix.Specifically,Schatten-norm can be imposed to approximate the low-rank constraints and obtain a better lowrank representation.Then,we design and adopt soft label matrix in source domain to learn a more flexible classifier and enhance the discriminative ability of target data.Besides,due to the nonconvexity of Schatten-norm,we design an efficient alternative algorithm IALM to solve it.Finally,experimental results on several public transfer tasks demonstrate the effectiveness of NDTSL compared with several state-of-the-art methods.展开更多
在图像语义分割领域,无监督领域自适应技术的发展有效降低了模型对标注数据的依赖,提升了自动驾驶等智能系统的效率和广泛适用性。针对无监督领域自适应技术在新场景泛化能力有限及在稀有类别中分割效果差的问题,文章提出了一种基于强...在图像语义分割领域,无监督领域自适应技术的发展有效降低了模型对标注数据的依赖,提升了自动驾驶等智能系统的效率和广泛适用性。针对无监督领域自适应技术在新场景泛化能力有限及在稀有类别中分割效果差的问题,文章提出了一种基于强弱一致性的无监督领域自适应语义分割算法。算法首先通过增加特征级别的增强,拓展图像增强空间的维度,改善了只利用图像级增强局限性。其次,采用基于能量分数的伪标签筛选方法,筛选出足够接近当前训练数据的样本赋予伪标签,避免了使用Softmax置信度方法在稀有类别中存在局限性,使模型更新更加稳健。最后,构建结合图像级别增强和特征级别增强的双重一致性框架,更充分的利用一致性训练,进一步提高模型的泛化能力。实验结果证明,提出的方法在GTA5-to-Cityscapes公开数据集中平均交并比指标(mean Intersection over Union,mIoU)可提升至52.6%,较PixMatch算法,性能提升了4.3%。展开更多
Unsupervised Domain Adaptation(UDA)intends to achieve excellent results by transferring knowledge from labeled source domains to unlabeled target domains in which the data or label distribution changes.Previous UDA me...Unsupervised Domain Adaptation(UDA)intends to achieve excellent results by transferring knowledge from labeled source domains to unlabeled target domains in which the data or label distribution changes.Previous UDA methods have acquired great success when labels in the source domain are pure.However,even the acquisition of scare clean labels in the source domain needs plenty of costs as well.In the presence of label noise in the source domain,the traditional UDA methods will be seriously degraded as they do not deal with the label noise.In this paper,we propose an approach named Robust Self-training with Label Refinement(RSLR)to address the above issue.RSLR adopts the self-training framework by maintaining a Labeling Network(LNet)on the source domain,which is used to provide confident pseudo-labels to target samples,and a Target-specific Network(TNet)trained by using the pseudo-labeled samples.To combat the effect of label noise,LNet progressively distinguishes and refines the mislabeled source samples.In combination with class rebalancing to combat the label distribution shift issue,RSLR achieves effective performance on extensive benchmark datasets.展开更多
文摘In Unsupervised Domain Adaptation(UDA)for person re-identification(re-ID),the primary challenge is reducing the distribution discrepancy between the source and target domains.This can be achieved by implicitly or explicitly constructing an appropriate intermediate domain to enhance recognition capability on the target domain.Implicit construction is difficult due to the absence of intermediate state supervision,making smooth knowledge transfer from the source to the target domain a challenge.To explicitly construct the most suitable intermediate domain for the model to gradually adapt to the feature distribution changes from the source to the target domain,we propose the Minimal Transfer Cost Framework(MTCF).MTCF considers all scenarios of the intermediate domain during the transfer process,ensuring smoother and more efficient domain alignment.Our framework mainly includes threemodules:Intermediate Domain Generator(IDG),Cross-domain Feature Constraint Module(CFCM),and Residual Channel Space Module(RCSM).First,the IDG Module is introduced to generate all possible intermediate domains,ensuring a smooth transition of knowledge fromthe source to the target domain.To reduce the cross-domain feature distribution discrepancy,we propose the CFCM Module,which quantifies the difficulty of knowledge transfer and ensures the diversity of intermediate domain features and their semantic relevance,achieving alignment between the source and target domains by incorporating mutual information and maximum mean discrepancy.We also design the RCSM,which utilizes attention mechanism to enhance the model’s focus on personnel features in low-resolution images,improving the accuracy and efficiency of person re-ID.Our proposed method outperforms existing technologies in all common UDA re-ID tasks and improves the Mean Average Precision(mAP)by 2.3%in the Market to Duke task compared to the state-of-the-art(SOTA)methods.
基金This paper was supported by the National Natural Science Foundation of China(61772286,61802208,and 61876089)China Postdoctoral Science Foundation Grant 2019M651923Natural Science Foundation of Jiangsu Province of China(BK0191381).
文摘:Cross-project defect prediction(CPDP)aims to predict the defects on target project by using a prediction model built on source projects.The main problem in CPDP is the huge distribution gap between the source project and the target project,which prevents the prediction model from performing well.Most existing methods overlook the class discrimination of the learned features.Seeking an effective transferable model from the source project to the target project for CPDP is challenging.In this paper,we propose an unsupervised domain adaptation based on the discriminative subspace learning(DSL)approach for CPDP.DSL treats the data from two projects as being from two domains and maps the data into a common feature space.It employs crossdomain alignment with discriminative information from different projects to reduce the distribution difference of the data between different projects and incorporates the class discriminative information.Specifically,DSL first utilizes subspace learning based domain adaptation to reduce the distribution gap of data between different projects.Then,it makes full use of the class label information of the source project and transfers the discrimination ability of the source project to the target project in the common space.Comprehensive experiments on five projects verify that DSL can build an effective prediction model and improve the performance over the related competing methods by at least 7.10%and 11.08%in terms of G-measure and AUC.
文摘Domain shift is when the data used in training does not match the ones it will be applied to later on under similar conditions.Domain shift will reduce accuracy in results.To prevent this,domain adaptation is done,which adapts the pre-trained model to the target domain.In real scenarios,the availability of labels for target data is rare thus resulting in unsupervised domain adaptation.Herein,we propose an innovative approach where source-free domain adaptation models and Generative Adversarial Networks(GANs)are integrated to improve the performance of computer vision or robotic vision-based systems in our study.Cosine Generative Adversarial Network(CosGAN)is developed as a GAN that uses cosine embedding loss to handle issues associated with unsupervised source-relax domain adaptations.For less complex architecture,the CosGAN training process has two steps that produce results almost comparable to other state-of-the-art techniques.The efficiency of CosGAN was compared by conducting experiments using benchmarked datasets.The approach was evaluated on different datasets and experimental results show superiority over existing state-of-the-art methods in terms of accuracy as well as generalization ability.This technique has numerous applications including wheeled robots,autonomous vehicles,warehouse automation,and all image-processing-based automation tasks so it can reshape the field of robotic vision with its ability to make robots adapt to new tasks and environments efficiently without requiring additional labeled data.It lays the groundwork for future expansions in robotic vision and applications.Although GAN provides a variety of outstanding features,it also increases the risk of instability and over-fitting of the training data thus making the data difficult to converge.
基金supported by National Key R&D Program of China(2021YFB3100800)National Natural Science Foundation of China(62271090)+1 种基金Chongqing Natural Science Fund(cstc2021jcyjjqX0023)supported by Huawei computational power of Chongqing Artificial Intelligence Innovation Center.
文摘Labeled data scarcity of an interested domain is often a serious problem in machine learning.Leveraging the labeled data from other semantic-related yet co-variate shifted source domain to facilitate the interested domain is a consensus.In order to solve the domain shift between domains and reduce the learning ambiguity,unsupervised domain adaptation(UDA)greatly promotes the transferability of model parameters.However,the dilemma of over-fitting(negative transfer)and under-fitting(under-adaptation)is always an overlooked challenge and potential risk.In this paper,we rethink the shallow learning paradigm and this intractable over/under-fitting problem,and propose a safer UDA model,coined as Bilateral Co-Transfer(BCT),which is essentially beyond previous well-known unilateral transfer.With bilateral co-transfer between domains,the risk of over/under-fitting is therefore largely reduced.Technically,the proposed BCT is a symmetrical structure,with joint distribution discrepancy(JDD)modeled for domain alignment and category discrimination.Specifically,a symmetrical bilateral transfer(SBT)loss between source and target domains is proposed under the philosophy of mutual checks and balances.First,each target sample is represented by source samples with low-rankness constraint in a common subspace,such that the most informative and transferable source data can be used to alleviate negative transfer.Second,each source sample is symmetrically and sparsely represented by target samples,such that the most reliable target samples can be exploited to tackle underadaptation.Experiments on various benchmarks show that our BCT outperforms many previous outstanding work.
基金supported by the National Natural Science Foundation of China(Grant No.61922087)the Huxiang Young Talents Program of Hunan Province(2021RC3070).
文摘Unsupervised transfer subspace learning is one of the challenging and important topics in domain adaptation,which aims to classify unlabeled target data by using source domain information.The traditional transfer subspace learning methods often impose low-rank constraints,i.e.,trace norm,to preserve data structural information of different domains.However,trace norm is only the convex surrogate to approximate the ideal low-rank constraints and may make their solutions seriously deviate from the original optimums.In addition,the traditional methods directly use the strict labels of source domain,which is difficult to deal with label noise.To solve these problems,we propose a novel nonconvex and discriminative transfer subspace learning method named NDTSL by incorporating Schatten-norm and soft label matrix.Specifically,Schatten-norm can be imposed to approximate the low-rank constraints and obtain a better lowrank representation.Then,we design and adopt soft label matrix in source domain to learn a more flexible classifier and enhance the discriminative ability of target data.Besides,due to the nonconvexity of Schatten-norm,we design an efficient alternative algorithm IALM to solve it.Finally,experimental results on several public transfer tasks demonstrate the effectiveness of NDTSL compared with several state-of-the-art methods.
文摘在图像语义分割领域,无监督领域自适应技术的发展有效降低了模型对标注数据的依赖,提升了自动驾驶等智能系统的效率和广泛适用性。针对无监督领域自适应技术在新场景泛化能力有限及在稀有类别中分割效果差的问题,文章提出了一种基于强弱一致性的无监督领域自适应语义分割算法。算法首先通过增加特征级别的增强,拓展图像增强空间的维度,改善了只利用图像级增强局限性。其次,采用基于能量分数的伪标签筛选方法,筛选出足够接近当前训练数据的样本赋予伪标签,避免了使用Softmax置信度方法在稀有类别中存在局限性,使模型更新更加稳健。最后,构建结合图像级别增强和特征级别增强的双重一致性框架,更充分的利用一致性训练,进一步提高模型的泛化能力。实验结果证明,提出的方法在GTA5-to-Cityscapes公开数据集中平均交并比指标(mean Intersection over Union,mIoU)可提升至52.6%,较PixMatch算法,性能提升了4.3%。
基金supported by the National Key R&D Program of China(2022ZD0114801)the National Natural Science Foundation of China(Grant No.61906089)the Jiangsu Province Basic Research Program(BK20190408).
文摘Unsupervised Domain Adaptation(UDA)intends to achieve excellent results by transferring knowledge from labeled source domains to unlabeled target domains in which the data or label distribution changes.Previous UDA methods have acquired great success when labels in the source domain are pure.However,even the acquisition of scare clean labels in the source domain needs plenty of costs as well.In the presence of label noise in the source domain,the traditional UDA methods will be seriously degraded as they do not deal with the label noise.In this paper,we propose an approach named Robust Self-training with Label Refinement(RSLR)to address the above issue.RSLR adopts the self-training framework by maintaining a Labeling Network(LNet)on the source domain,which is used to provide confident pseudo-labels to target samples,and a Target-specific Network(TNet)trained by using the pseudo-labeled samples.To combat the effect of label noise,LNet progressively distinguishes and refines the mislabeled source samples.In combination with class rebalancing to combat the label distribution shift issue,RSLR achieves effective performance on extensive benchmark datasets.
文摘具有混合记忆的自步对比学习(Self-paced Contrastive Learning,SpCL)通过集群聚类生成不同级别的伪标签来训练网络,取得了较好的识别效果,然而该方法从源域和目标域中捕获的行人数据之间存在典型的分布差异,使得训练出的网络不能准确区别目标域和源域数据域特征。针对此问题,提出了双分支动态辅助对比学习(Dynamic Auxiliary Contrastive Learning,DACL)框架。该方法首先通过动态减小源域和目标域之间的局部最大平均差异(Local Maximum Mean Discrepancy,LMMD),以有效地学习目标域的域不变特征;其次,引入广义均值(Generalized Mean,GeM)池化策略,在特征提取后再进行特征聚合,使提出的网络能够自适应地聚合图像的重要特征;最后,在3个经典行人重识别数据集上进行了仿真实验,提出的DACL与性能次之的无监督域自适应行人重识别方法相比,mAP和rank-1在Market1501数据集上分别增加了6.0个百分点和2.2个百分点,在MSMT17数据集上分别增加了2.8个百分点和3.6个百分点,在Duke数据集上分别增加了1.7个百分点和2.1个百分点。
