Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning
复制标题
DOI：
10.1109/tpami.2016.2535231
复制
发表时间：
2017-01-01
影响因子：
23.6
通讯作者：
Schmid, Cordelia
中科院分区：
文献类型：
--
作者：
Cinbis, Ramazan Gokberk;Verbeek, Jakob;Schmid, Cordelia
目标类别定位是计算机视觉中的一个具有挑战性的问题。标准的监督训练需要对象实例的边界框注释。在弱监督学习中，这种耗时的标注过程被绕过。在这种情况下，监督信息被限制为指示图像中对象实例的不存在/存在的二进制标签，而不包括它们的位置。我们遵循多示例学习的方法，迭代地训练检测器，并在正向训练图像中推断目标位置。我们的主要贡献是一种多重多实例学习过程，它防止训练过早锁定错误的对象位置。当使用诸如Fisher矢量和卷积神经网络特征之类的高维表示时，该过程尤其重要。我们还提出了一种窗口细化方法，通过引入客观性先验来提高定位精度。我们使用PASCALVOC 2007数据集进行了详细的实验评估，验证了该方法的有效性。
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learning. In this case, the supervised information is restricted to binary labels that indicate the absence/presence of object instances in the image, without their locations. We follow a multiple-instance learning approach that iteratively trains the detector and infers the object locations in the positive training images. Our main contribution is a multi-fold multiple instance learning procedure, which prevents training from prematurely locking onto erroneous object locations. This procedure is particularly important when using high-dimensional representations, such as Fisher vectors and convolutional neural network features. We also propose a window refinement method, which improves the localization accuracy by incorporating an objectness prior. We present a detailed experimental evaluation using the PASCALVOC 2007 dataset, which verifies the effectiveness of our approach.