It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, an...It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The proba- bility distributions defined over the graphs capture the statistical variability of these structures. These proba- bility models can be learnt from training data with lim- ited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normaliza- tion constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain compu- rationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines （SVMs） and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple- instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that rained by using better bounds better results can be ob- and approximations.展开更多
针对建筑元素特征提取不全、相似建筑风格识别困难等问题,提出一种显著区域抑制与多尺度特征融合(salient region suppression and multi-scale feature fusion,SRSMSFF)的建筑风格识别方法。首先,采用改进的Resnet18提取初始建筑特征...针对建筑元素特征提取不全、相似建筑风格识别困难等问题,提出一种显著区域抑制与多尺度特征融合(salient region suppression and multi-scale feature fusion,SRSMSFF)的建筑风格识别方法。首先,采用改进的Resnet18提取初始建筑特征。然后,设计显著区域抑制模块(salient region suppression module,SRSM),通过隐藏最具判别性区域,引导网络学习潜在区域的特征,并设计多尺度特征融合网络(multi-scale feature fusion,MSFF),将多尺度结构与显著区域抑制相结合,以获取更完整的建筑元素特征。接着,利用通道注意力赋予各通道相应的权重,以突出重要的通道信息。最后,大边距度量损失函数(large-margin Softmax loss function,L-Softmax)通过最大化特征嵌入空间的决策边界,改善相似建筑风格的识别。在公共建筑数据集10类、25类及自建中国古建筑数据集上的实验结果表明,本文方法的准确率分别达到80.21%、64.4%和88.21%,其性能优于目前的先进方法。展开更多
文摘汉语组块分析是中文信息处理领域中一项重要的子任务.在一种新的结构化SVMs(support vector machines)模型的基础上,提出一种基于大间隔方法的汉语组块分析方法.首先,针对汉语组块分析问题设计了序列化标注模型;然后根据大间隔思想给出判别式的序列化标注函数的优化目标,并应用割平面算法实现对特征参数的近似优化训练.针对组块识别问题设计了一种改进的F1损失函数,使得F1损失值能够依据每个句子的实际长度进行相应的调整,从而能够引入更有效的约束不等式.通过在滨州中文树库CTB4数据集上的实验数据显示,基于改进的F1损失函数所产生的识别结果优于Hamming损失函数,各种类型组块识别的总的F1值为91.61%,优于CRFs(conditional random fields)和SVMs方法.
文摘It is attractive to formulate problems in computer vision and related fields in term of probabilis- tic estimation where the probability models are defined over graphs, such as grammars. The graphical struc- tures, and the state variables defined over them, give a rich knowledge representation which can describe the complex structures of objects and images. The proba- bility distributions defined over the graphs capture the statistical variability of these structures. These proba- bility models can be learnt from training data with lim- ited amounts of supervision. But learning these models suffers from the difficulty of evaluating the normaliza- tion constant, or partition function, of the probability distributions which can be extremely computationally demanding. This paper shows that by placing bounds on the normalization constant we can obtain compu- rationally tractable approximations. Surprisingly, for certain choices of loss functions, we obtain many of the standard max-margin criteria used in support vector machines （SVMs） and hence we reduce the learning to standard machine learning methods. We show that many machine learning methods can be obtained in this way as approximations to probabilistic methods including multi-class max-margin, ordinal regression, max-margin Markov networks and parsers, multiple- instance learning, and latent SVM. We illustrate this work by computer vision applications including image labeling, object detection and localization, and motion estimation. We speculate that rained by using better bounds better results can be ob- and approximations.
文摘针对建筑元素特征提取不全、相似建筑风格识别困难等问题,提出一种显著区域抑制与多尺度特征融合(salient region suppression and multi-scale feature fusion,SRSMSFF)的建筑风格识别方法。首先,采用改进的Resnet18提取初始建筑特征。然后,设计显著区域抑制模块(salient region suppression module,SRSM),通过隐藏最具判别性区域,引导网络学习潜在区域的特征,并设计多尺度特征融合网络(multi-scale feature fusion,MSFF),将多尺度结构与显著区域抑制相结合,以获取更完整的建筑元素特征。接着,利用通道注意力赋予各通道相应的权重,以突出重要的通道信息。最后,大边距度量损失函数(large-margin Softmax loss function,L-Softmax)通过最大化特征嵌入空间的决策边界,改善相似建筑风格的识别。在公共建筑数据集10类、25类及自建中国古建筑数据集上的实验结果表明,本文方法的准确率分别达到80.21%、64.4%和88.21%,其性能优于目前的先进方法。
