Salient Object Detection via Multiple Instance Learning
Salient Object Detection via Multiple Instance Learning
复制标题
通过多实例学习进行显着目标检测
DOI：
10.1109/tip.2017.2669878
复制
发表时间：
2017-04-01
影响因子：
10.6
通讯作者：
Ruan, Xiang
中科院分区：
文献类型：
--
作者：
Huang, Fang;Qi, Jinqing;Ruan, Xiang
目标建议是一系列包含感兴趣目标的候选片段，作为预处理，广泛应用于各种视觉任务中。然而，大多数现有的显着性方法只利用该建议来计算位置先验。在本文中，我们自然地将建议视为多实例学习（MIL）的实例包，其中实例是建议中包含的超像素，并将显着性检测问题公式化为MIL任务（即，使用MIL框架中的分类器预测实例的标签）。该方法允许在基于袋级表示找到决策边界时具有一定的灵活性，并且可以从模糊的提议中识别突出的超像素。此外，我们还将MIL引入了一种优化机制，该机制迭代地将训练包从简单的训练包更新为复杂的训练包，以学习强大的模型。当将优化模型应用于现有的显着性方法时，可以一致地实现显着的改进。大量的实验表明，所提出的算法表现良好，对国家的最先进的显着性检测方法在几个基准数据集。
Object proposals are a series of candidate segments containing the objects of interest, which are taken as preprocessing and widely applied in various vision tasks. However, most of existing saliency approaches only utilizes the proposals to compute a location prior. In this paper, we naturally take the proposals as the bags of instances of multiple instances learning (MIL), where the instances are the superpixels contained in the proposals, and formulate saliency detection problem as an MIL task (i.e., predict the labels of instances using the classifier in the MIL framework). This method allows some flexibility in finding a decision boundary based on the bag-level representations and can identify salient superpixels from ambiguous proposals. In addition, we introduce the MIL to an optimization mechanism, which iteratively updates training bags from easy to complex ones to learn a strong model. The significant improvement can be consistently achieved when applying the optimization model to existing saliency approaches. Extensive experiments demonstrate that the proposed algorithms perform favorably against the state-of-art saliency detection methods on several benchmark data sets.