在图像分类的实际应用过程中,部分类别可能完全没有带标签的训练数据。零样本学习(ZSL)的目的是将带标签类别的图像特征等知识迁移到无标签的类别上,实现无标签类别的正确分类。现有方法在测试时无法显式地区分输入图像属于已知类还是...在图像分类的实际应用过程中,部分类别可能完全没有带标签的训练数据。零样本学习(ZSL)的目的是将带标签类别的图像特征等知识迁移到无标签的类别上,实现无标签类别的正确分类。现有方法在测试时无法显式地区分输入图像属于已知类还是未知类,很大程度上导致未知类在传统设定下的ZSL和广义设定下的ZSL(GZSL)上的预测效果相差甚远。为此,提出一种融合视觉误差与属性语义信息的方法来缓解零样本图像分类中的预测偏置问题。首先,设计一种半监督学习方式的生成对抗网络架构来获取视觉误差信息,由此预测图像是否属于已知类;然后,提出融合属性语义信息的零样本图像分类网络来实现零样本图像分类;最后,测试融合视觉误差与属性语义的零样本图像分类方法在数据集AwA2和CUB上的效果。实验结果表明,与对比模型相比,所提方法有效缓解了预测偏置问题,其调和指标H在AwA2(Animal with Attributes)上提升了31.7个百分点,在CUB(Caltech-UCSD-Birds-200-2011)上提升了8.7个百分点。展开更多
In this work, we use a deep learning method to tackle the Zero-Shot Learning(ZSL) problem in tactile material recognition by incorporating the advanced semantic information into a training model. Our main technical co...In this work, we use a deep learning method to tackle the Zero-Shot Learning(ZSL) problem in tactile material recognition by incorporating the advanced semantic information into a training model. Our main technical contribution is our proposal of an end-to-end deep learning framework for solving the tactile ZSL problem. In this framework, we use a Convolutional Neural Network(CNN) to extract the spatial features and Long Short-Term Memory(LSTM) to extract the temporal features in dynamic tactile sequences, and develop a loss function suitable for the ZSL setting. We present the results of experimental evaluations on publicly available datasets, which show the effectiveness of the proposed method.展开更多
文摘在图像分类的实际应用过程中,部分类别可能完全没有带标签的训练数据。零样本学习(ZSL)的目的是将带标签类别的图像特征等知识迁移到无标签的类别上,实现无标签类别的正确分类。现有方法在测试时无法显式地区分输入图像属于已知类还是未知类,很大程度上导致未知类在传统设定下的ZSL和广义设定下的ZSL(GZSL)上的预测效果相差甚远。为此,提出一种融合视觉误差与属性语义信息的方法来缓解零样本图像分类中的预测偏置问题。首先,设计一种半监督学习方式的生成对抗网络架构来获取视觉误差信息,由此预测图像是否属于已知类;然后,提出融合属性语义信息的零样本图像分类网络来实现零样本图像分类;最后,测试融合视觉误差与属性语义的零样本图像分类方法在数据集AwA2和CUB上的效果。实验结果表明,与对比模型相比,所提方法有效缓解了预测偏置问题,其调和指标H在AwA2(Animal with Attributes)上提升了31.7个百分点,在CUB(Caltech-UCSD-Birds-200-2011)上提升了8.7个百分点。
基金supported in part by the National Natural Science Foundation of China (Nos. 61673238, 61703284, and 61327809)the Beijing Municipal Science and Technology Commission (No. D171100005017002)
文摘In this work, we use a deep learning method to tackle the Zero-Shot Learning(ZSL) problem in tactile material recognition by incorporating the advanced semantic information into a training model. Our main technical contribution is our proposal of an end-to-end deep learning framework for solving the tactile ZSL problem. In this framework, we use a Convolutional Neural Network(CNN) to extract the spatial features and Long Short-Term Memory(LSTM) to extract the temporal features in dynamic tactile sequences, and develop a loss function suitable for the ZSL setting. We present the results of experimental evaluations on publicly available datasets, which show the effectiveness of the proposed method.
