Feature correspondence is a crucial aspect of various computer vision and robot vision tasks.Unlike traditional optimization-based matching techniques,researchers have recently adopted a learning-based approach for ma...Feature correspondence is a crucial aspect of various computer vision and robot vision tasks.Unlike traditional optimization-based matching techniques,researchers have recently adopted a learning-based approach for matching,but these methods face challenges in dealing with outlier features.This paper presents an outlier robust feature correspondence method that employs a pruned attentional graph neural network and a matching layer to address the outlier issue.Additionally,the authors introduce a modified cross-entropy matching loss to handle the outlier problem.As a result,the proposed method significantly enhances the performance of learning-based matching algorithms in the presence of outlier features.Benchmark experiments confirm the effectiveness of the proposed approach.展开更多
When encountering the distribution shift between the source(training) and target(test) domains, domain adaptation attempts to adjust the classifiers to be capable of dealing with different domains. Previous domain ada...When encountering the distribution shift between the source(training) and target(test) domains, domain adaptation attempts to adjust the classifiers to be capable of dealing with different domains. Previous domain adaptation research has achieved a lot of success both in theory and practice under the assumption that all the examples in the source domain are welllabeled and of high quality. However, the methods consistently lose robustness in noisy settings where data from the source domain have corrupted labels or features which is common in reality. Therefore, robust domain adaptation has been introduced to deal with such problems. In this paper, we attempt to solve two interrelated problems with robust domain adaptation:distribution shift across domains and sample noises of the source domain. To disentangle these challenges, an optimal transport approach with low-rank constraints is applied to guide the domain adaptation model training process to avoid noisy information influence. For the domain shift problem, the optimal transport mechanism can learn the joint data representations between the source and target domains using a measurement of discrepancy and preserve the discriminative information. The rank constraint on the transport matrix can help recover the corrupted subspace structures and eliminate the noise to some extent when dealing with corrupted source data. The solution to this relaxed and regularized optimal transport framework is a convex optimization problem that can be solved using the Augmented Lagrange Multiplier method, whose convergence can be mathematically proved. The effectiveness of the proposed method is evaluated through extensive experiments on both synthetic and real-world datasets.展开更多
This paper introduces a novel framework,i.e.,RFPose-OT,to enable three-dimensional(3D)human pose estimation from radio frequency(RF)signals.Different from existing methods that predict human poses from RF signals at t...This paper introduces a novel framework,i.e.,RFPose-OT,to enable three-dimensional(3D)human pose estimation from radio frequency(RF)signals.Different from existing methods that predict human poses from RF signals at the signal level directly,we consider the structure difference between the RF signals and the human poses,propose a transformation of the RF signals to the pose domain at the feature level based on the optimal transport(OT)theory,and generate human poses from the transformed features.To evaluate RFPose-OT,we build a radio system and a multi-view camera system to acquire the RF signal data and the ground-truth human poses.The experimental results in a basic indoor environment,an occlusion indoor environment,and an outdoor environment demonstrate that RFPose-OT can predict 3D human poses with higher precision than state-of-the-art methods.展开更多
现实世界中训练数据和测试数据往往存在分布差异,导致基于独立同分布假设的模型丧失鲁棒性.无监督域自适应是一种重要解决方法,极具应用价值.鉴于此,国内外研究者进行大量理论基础和方法技术的研究,促进了很多应用领域的发展,包括自动...现实世界中训练数据和测试数据往往存在分布差异,导致基于独立同分布假设的模型丧失鲁棒性.无监督域自适应是一种重要解决方法,极具应用价值.鉴于此,国内外研究者进行大量理论基础和方法技术的研究,促进了很多应用领域的发展,包括自动驾驶、智慧医疗等.但是,目前主流的方法仍存在一些问题:源域和目标域的概率分布距离是否能真正代表它们之间的差异,以及如何更准确地度量2个分布之间的差异,仍然是一个值得探讨的问题.同时,如何更有效地利用伪标签,也是一个值得继续探索的问题.提出了反向伪标签最优化传输(backward pseudo-label and optimal transport,BPLOT),不仅利用瓦瑟斯坦距离和格罗莫夫-瓦瑟斯坦距离,从最优化特征-拓扑传输的角度更准确地计算了2个分布之间的差异;而且提出了反向验证伪标签的模块来更有效地利用伪标签,在训练过程中验证伪标签的质量.将所提出的方法在多个无监督域自适应的数据集上进行了实验验证.实验结果表明,BPLOT模型的效果超过了所有对比的基准方法.展开更多
基于深度学习的个性化新闻推荐方法通常采用全量更新训练模型.然而,全量更新需要不断整合新数据形成新的训练集,虽然可以保障模型性能,但训练效率低下.另外,出于数据隐私和存储考虑,现实场景下的应用通常不会保留所有历史数据导致全量...基于深度学习的个性化新闻推荐方法通常采用全量更新训练模型.然而,全量更新需要不断整合新数据形成新的训练集,虽然可以保障模型性能,但训练效率低下.另外,出于数据隐私和存储考虑,现实场景下的应用通常不会保留所有历史数据导致全量更新难以为继.增量学习是目前广泛采用的有效解决方法.然而,基于增量学习的新闻推荐模型也存在着新的挑战——灾难性遗忘问题,常见的解决策略有基于正则化和基于回放的方法.基于正则化的方法局限于个体样本在新任务中学习到的特征和原始网络的响应特征之间的对齐或空间几何结构匹配,缺乏全局视觉.基于回放的方法重放过往任务数据,可能导致数据隐私泄漏.为了解决以上不足,本文提出了基于最优传输和知识回放(Optimal Transport and Knowledge Replay)的新闻推荐模型增量学习方法OT-KR.OT-KR方法通过联合分布知识提取器重构联合分布知识特征集合,并且使用最优传输理论在训练过程中最小化新任务和旧任务间的分布差异,确保新模型学习到的域分布可以同时拟合旧任务和新任务,实现知识融合.特别地,为了缓解数据隐私泄漏问题,OT-KR方法仅保存模型参数而非样本作为知识进行回放,同时,借鉴多教师知识蒸馏思想让新任务上的模型可以同时融合所有教师流中的分布信息,并根据任务的学习次序分配权重.通过在公开新闻推荐数据集上开展实验,结果表明OT-KR方法的推荐性能优于基于目前主流增量学习技术的新闻推荐方法,在AUC和NDCG@10两个指标上比目前最优性能平均提高了0.55%和0.47%,同时,能够很好地平衡模型的推荐性能和训练效率.展开更多
基金supported by the National Natural Science Foundation of China under Grant Nos.61973301,61972020Youth Innovation Promotion Association CAS。
文摘Feature correspondence is a crucial aspect of various computer vision and robot vision tasks.Unlike traditional optimization-based matching techniques,researchers have recently adopted a learning-based approach for matching,but these methods face challenges in dealing with outlier features.This paper presents an outlier robust feature correspondence method that employs a pruned attentional graph neural network and a matching layer to address the outlier issue.Additionally,the authors introduce a modified cross-entropy matching loss to handle the outlier problem.As a result,the proposed method significantly enhances the performance of learning-based matching algorithms in the presence of outlier features.Benchmark experiments confirm the effectiveness of the proposed approach.
基金supported by the National Natural Science Foundation of China (62206204,62176193)the Natural Science Foundation of Hubei Province,China (2023AFB705)the Natural Science Foundation of Chongqing,China (CSTB2023NSCQ-MSX0932)。
文摘When encountering the distribution shift between the source(training) and target(test) domains, domain adaptation attempts to adjust the classifiers to be capable of dealing with different domains. Previous domain adaptation research has achieved a lot of success both in theory and practice under the assumption that all the examples in the source domain are welllabeled and of high quality. However, the methods consistently lose robustness in noisy settings where data from the source domain have corrupted labels or features which is common in reality. Therefore, robust domain adaptation has been introduced to deal with such problems. In this paper, we attempt to solve two interrelated problems with robust domain adaptation:distribution shift across domains and sample noises of the source domain. To disentangle these challenges, an optimal transport approach with low-rank constraints is applied to guide the domain adaptation model training process to avoid noisy information influence. For the domain shift problem, the optimal transport mechanism can learn the joint data representations between the source and target domains using a measurement of discrepancy and preserve the discriminative information. The rank constraint on the transport matrix can help recover the corrupted subspace structures and eliminate the noise to some extent when dealing with corrupted source data. The solution to this relaxed and regularized optimal transport framework is a convex optimization problem that can be solved using the Augmented Lagrange Multiplier method, whose convergence can be mathematically proved. The effectiveness of the proposed method is evaluated through extensive experiments on both synthetic and real-world datasets.
基金supported by the National Natural Science Foundation of China(Nos.62201542 and 62172381)the National Key R&D Programmes of China(Nos.2022YFC2503405 and 2022YFC0869800)+1 种基金the Fellowship of China Postdoctoral Science Foundation(No.2022M723069)the Fundamental Research Funds for the Central Universities,China。
文摘This paper introduces a novel framework,i.e.,RFPose-OT,to enable three-dimensional(3D)human pose estimation from radio frequency(RF)signals.Different from existing methods that predict human poses from RF signals at the signal level directly,we consider the structure difference between the RF signals and the human poses,propose a transformation of the RF signals to the pose domain at the feature level based on the optimal transport(OT)theory,and generate human poses from the transformed features.To evaluate RFPose-OT,we build a radio system and a multi-view camera system to acquire the RF signal data and the ground-truth human poses.The experimental results in a basic indoor environment,an occlusion indoor environment,and an outdoor environment demonstrate that RFPose-OT can predict 3D human poses with higher precision than state-of-the-art methods.
文摘现实世界中训练数据和测试数据往往存在分布差异,导致基于独立同分布假设的模型丧失鲁棒性.无监督域自适应是一种重要解决方法,极具应用价值.鉴于此,国内外研究者进行大量理论基础和方法技术的研究,促进了很多应用领域的发展,包括自动驾驶、智慧医疗等.但是,目前主流的方法仍存在一些问题:源域和目标域的概率分布距离是否能真正代表它们之间的差异,以及如何更准确地度量2个分布之间的差异,仍然是一个值得探讨的问题.同时,如何更有效地利用伪标签,也是一个值得继续探索的问题.提出了反向伪标签最优化传输(backward pseudo-label and optimal transport,BPLOT),不仅利用瓦瑟斯坦距离和格罗莫夫-瓦瑟斯坦距离,从最优化特征-拓扑传输的角度更准确地计算了2个分布之间的差异;而且提出了反向验证伪标签的模块来更有效地利用伪标签,在训练过程中验证伪标签的质量.将所提出的方法在多个无监督域自适应的数据集上进行了实验验证.实验结果表明,BPLOT模型的效果超过了所有对比的基准方法.
文摘基于深度学习的个性化新闻推荐方法通常采用全量更新训练模型.然而,全量更新需要不断整合新数据形成新的训练集,虽然可以保障模型性能,但训练效率低下.另外,出于数据隐私和存储考虑,现实场景下的应用通常不会保留所有历史数据导致全量更新难以为继.增量学习是目前广泛采用的有效解决方法.然而,基于增量学习的新闻推荐模型也存在着新的挑战——灾难性遗忘问题,常见的解决策略有基于正则化和基于回放的方法.基于正则化的方法局限于个体样本在新任务中学习到的特征和原始网络的响应特征之间的对齐或空间几何结构匹配,缺乏全局视觉.基于回放的方法重放过往任务数据,可能导致数据隐私泄漏.为了解决以上不足,本文提出了基于最优传输和知识回放(Optimal Transport and Knowledge Replay)的新闻推荐模型增量学习方法OT-KR.OT-KR方法通过联合分布知识提取器重构联合分布知识特征集合,并且使用最优传输理论在训练过程中最小化新任务和旧任务间的分布差异,确保新模型学习到的域分布可以同时拟合旧任务和新任务,实现知识融合.特别地,为了缓解数据隐私泄漏问题,OT-KR方法仅保存模型参数而非样本作为知识进行回放,同时,借鉴多教师知识蒸馏思想让新任务上的模型可以同时融合所有教师流中的分布信息,并根据任务的学习次序分配权重.通过在公开新闻推荐数据集上开展实验,结果表明OT-KR方法的推荐性能优于基于目前主流增量学习技术的新闻推荐方法,在AUC和NDCG@10两个指标上比目前最优性能平均提高了0.55%和0.47%,同时,能够很好地平衡模型的推荐性能和训练效率.
