IEEE Trans Pattern Anal Mach Intell. 2018 Jul;40(7):1653-1667. doi: 10.1109/TPAMI.2017.2723401. Epub 2017 Jul 4.
Learning a classifier from ambiguously labeled face images is challenging since training images are not always explicitly-labeled. For instance, face images of two persons in a news photo are not explicitly labeled by their names in the caption. We propose a Matrix Completion for Ambiguity Resolution (MCar) method for predicting the actual labels from ambiguously labeled images. This step is followed by learning a standard supervised classifier from the disambiguated labels to classify new images. To prevent the majority labels from dominating the result of MCar, we generalize MCar to a weighted MCar (WMCar) that handles label imbalance. Since WMCar outputs a soft labeling vector of reduced ambiguity for each instance, we can iteratively refine it by feeding it as the input to WMCar. Nevertheless, such an iterative implementation can be affected by the noisy soft labeling vectors, and thus the performance may degrade. Our proposed Iterative Candidate Elimination (ICE) procedure makes the iterative ambiguity resolution possible by gradually eliminating a portion of least likely candidates in ambiguously labeled faces. We further extend MCar to incorporate the labeling constraints among instances when such prior knowledge is available. Compared to existing methods, our approach demonstrates improvements on several ambiguously labeled datasets.
从标注不明确的人脸图像中学习分类器是具有挑战性的，因为训练图像并不总是明确标注的。例如，新闻照片中两个人的人脸图像在标题中并没有明确标注他们的名字。我们提出了一种用于解决歧义的矩阵补全方法（MCar），用于从标注不明确的图像中预测实际标签。然后，我们可以从去歧义后的标签中学习标准的监督分类器，以对新图像进行分类。为了防止多数标签主导 MCar 的结果，我们将 MCar 推广到处理标签不平衡的加权 MCar（WMCar）。由于 WMCar 为每个实例输出一个歧义程度降低的软标签向量，我们可以通过将其作为输入馈送到 WMCar 来迭代地细化它。然而，这种迭代实现可能会受到噪声软标签向量的影响，从而导致性能下降。我们提出的迭代候选消除（ICE）过程通过逐步消除标注不明确的人脸中不太可能的候选对象的一部分，使得迭代歧义消除成为可能。当存在这种先验知识时，我们进一步将 MCar 扩展到可以整合实例之间的标注约束。与现有的方法相比，我们的方法在几个标注不明确的数据集上取得了改进。
