In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple Instance Learning framework in which the current classifier is used to select the highest-confidence boxes in each image, which are treated as pseudo-ground truth in the next training iteration. However, the errors of an immature classifier can make the process drift, usually introducing many of false positives in the training dataset. To alleviate this problem, we propose in this paper a training protocol based on the self-paced learning paradigm. The main idea is to iteratively select a subset of images and boxes that are the most reliable, and use them for training. While in the past few years similar strategies have been adopted for SVMs and other classifiers, we are the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline. The method we propose is built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes. We show state-of-the-art results on Pascal VOC 2007, Pascal VOC 2010 and ILSVRC 2013. On ILSVRC 2013 our results based on a low-capacity AlexNet network outperform even those weakly-supervised approaches which are based on much higher-capacity networks.

中文翻译：

---

用于弱监督目标检测的自定进度深度学习


在弱监督场景中，对象检测器需要单独使用图像级注释进行训练。由于边界框级别的地面实况不可用，到目前为止提出的大多数解决方案都是基于迭代的多实例学习框架，其中当前的分类器用于选择每个图像中置信度最高的框，并对其进行处理作为下一次训练迭代中的伪地面事实。然而，不成熟的分类器的错误可能会使过程发生偏差，通常会在训练数据集中引入许多误报。为了缓解这个问题，我们在本文中提出了一种基于自定进度学习范式的培训协议。主要思想是迭代地选择最可靠的图像和框的子集，并将其用于训练。虽然在过去几年中，支持向量机和其他分类器也采用了类似的策略，但我们首次表明，自定进度方法可以在端到端训练管道中与基于深度网络的分类器一起使用。我们提出的方法建立在完全监督的 Fast-RCNN 架构之上，并且可以应用于将输入图像表示为一袋盒子的类似架构。我们在 Pascal VOC 2007、Pascal VOC 2010 和 ILSVRC 2013 上展示了最先进的结果。在 ILSVRC 2013 上，我们基于低容量 AlexNet 网络的结果甚至优于那些基于高容量的弱监督方法网络。