首页>
外国专利>
METHOD AND DEVICE FOR TRAINING MULTI-LABEL CLASSIFICATION MODEL
METHOD AND DEVICE FOR TRAINING MULTI-LABEL CLASSIFICATION MODEL
展开▼
机译:训练多标签分类模型的方法和装置
展开▼
页面导航
摘要
著录项
相似文献
摘要
Provided are a method and device for training a multi-label classification model capable of dynamically learning image features, enabling a feature extraction network to better adapt to task requirements, and providing good multi-label classification performance. The method comprises: determining, from a training dataset, n samples and a label matrix Yc*n corresponding to the n samples, where an element yi*j in the label matrix Yc*n indicates whether the ith sample comprises an object denoted by the jth label, and c indicates the number of labels related to the samples; using a feature extraction network to extract a feature matrix Xd*n of the n samples; using a feature mapping network to acquire a predicted label matrix for the feature matrix Xd*n, where an element in the predicted label matrix indicates a confidence value as to whether the ith sample comprises the object denoted by the jth label; and updating, according to the label matrix Yc*n and the predicted label matrix, a weight parameter Z and a feature mapping matrix Mc*d to train a multi-label classification model.
展开▼
机译:提供了一种用于训练能够动态学习图像特征的多标签分类模型的方法和设备,使得特征提取网络能够更好地适应任务要求,并提供良好的多标签分类性能。该方法包括:从训练数据集中确定 n I>个样本和对应于 n I>个样本的标签矩阵Y c * n Sub>,其中标签矩阵Y c * n Sub>中的元素y i * j Sub>指示第 i I>个样本是否包含由 j表示的对象 I>标签, c I>表示与样本相关的标签数量;使用特征提取网络提取 n I>个样本的特征矩阵X d * n Sub>;使用特征映射网络来获取特征矩阵X d * n Sub>的预测标签矩阵,其中预测标签矩阵中的元素指示关于 i I第样本包括第 j I>个标签表示的对象;根据标签矩阵Y c * n Sub>和预测的标签矩阵,加权参数Z和特征映射矩阵M c * d Sub>进行更新,标签分类模型。
展开▼