ML-MG: Multi-label Learning with Missing Labels Using a Mixed Graph
ML-MG: Multi-label Learning with Missing Labels Using a Mixed Graph
复制标题
DOI：
10.1109/iccv.2015.473
复制
发表时间：
2015-12
期刊：
影响因子：
--
通讯作者：
Baoyuan Wu;Siwei Lyu;Bernard Ghanem
中科院分区：
文献类型：
--
作者：
Baoyuan Wu;Siwei Lyu;Bernard Ghanem
这项工作的重点是缺失标签的多标签学习（MLML）问题，其目的是给每个测试实例贴上多个类别标签，给定训练实例有这些标签的不完整/部分集合（即它们的一些标签缺失）。为了处理丢失的标签，我们提出了一个统一的标签依赖模型，通过构建一个混合图，它联合采用（i）实例级相似性和类同现作为无向边和（ii）语义标签层次结构作为有向边。与大多数MLML方法不同，我们将此学习问题转换为凸二次矩阵优化问题，该问题鼓励训练标签一致性，并使用二次项和硬线性约束对两种类型的标签依赖性（即无向和有向边缘）进行编码。交替方向乘子法（ADMM）可以准确、高效地求解该问题。为了评估我们提出的方法，我们考虑两个流行的应用程序（图像和视频注释），标签层次结构可以从Wordnet中导出。实验结果表明，我们的方法实现了显着的改进，在性能和鲁棒性的最先进的方法丢失的标签。
This work focuses on the problem of multi-label learning with missing labels (MLML), which aims to label each test instance with multiple class labels given training instances that have an incomplete/partial set of these labels (i.e. some of their labels are missing). To handle missing labels, we propose a unified model of label dependencies by constructing a mixed graph, which jointly incorporates (i) instance-level similarity and class co-occurrence as undirected edges and (ii) semantic label hierarchy as directed edges. Unlike most MLML methods, We formulate this learning problem transductively as a convex quadratic matrix optimization problem that encourages training label consistency and encodes both types of label dependencies (i.e. undirected and directed edges) using quadratic terms and hard linear constraints. The alternating direction method of multipliers (ADMM) can be used to exactly and efficiently solve this problem. To evaluate our proposed method, we consider two popular applications (image and video annotation), where the label hierarchy can be derived from Wordnet. Experimental results show that our method achieves a significant improvement over state-of-the-art methods in performance and robustness to missing labels.