Keywords to visual categories: Multiple-instance learning forweakly supervised object categorization
Keywords to visual categories: Multiple-instance learning forweakly supervised object categorization
复制标题
DOI：
10.1109/cvpr.2008.4587632
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
Sudheendra Vijayanarasimhan;K. Grauman
中科院分区：
文献类型：
--
作者：
Sudheendra Vijayanarasimhan;K. Grauman
传统的图像分类监督方法依赖于手动注释（标记）的示例来学习良好的对象模型，这意味着它们的通用性和可扩展性在很大程度上取决于可用于帮助训练它们的人力资源。我们提出了一种无监督的方法来构造判别模型的类别，指定简单的名称。我们表明，多实例学习能够从基于关键字的搜索引擎返回的图像中恢复鲁棒的类别模型。通过将反映真实正面示例的预期稀疏性的约束纳入大幅度目标函数中，即使在可用文本注释不完善和模糊的情况下，我们的方法仍然是准确的。此外，我们展示了如何通过自动改进模糊标记示例的表示来迭代改进学习的分类器。我们用基准数据集演示了我们的方法，并表明它相对于最先进的无监督方法和传统的全监督技术都表现良好。
Conventional supervised methods for image categorization rely on manually annotated (labeled) examples to learn good object models, which means their generality and scalability depends heavily on the amount of human effort available to help train them. We propose an unsupervised approach to construct discriminative models for categories specified simply by their names. We show that multiple-instance learning enables the recovery of robust category models from images returned by keyword-based search engines. By incorporating constraints that reflect the expected sparsity of true positive examples into a large-margin objective function, our approach remains accurate even when the available text annotations are imperfect and ambiguous. In addition, we show how to iteratively improve the learned classifier by automatically refining the representation of the ambiguously labeled examples. We demonstrate our method with benchmark datasets, and show that it performs well relative to both state-of-the-art unsupervised approaches and traditional fully supervised techniques.