论文标题
从高质量的伪标签中学习一致性，用于弱监督物体本地化
Learning Consistency from High-quality Pseudo-labels for Weakly Supervised Object Localization
论文作者
论文摘要
伪监督的学习方法已被证明对弱监督的对象本地化任务有效。但是，有效性取决于深神经网络的强大正则能力。基于以下假设：本地化网络应在同一图像的不同版本上具有相似的位置预测，我们提出了一种两阶段的方法来学习更一致的定位。在第一阶段，我们提出了一个基于掩模的伪标签生成器算法，并使用伪监督的学习方法来初始化对象本地化网络。在第二阶段，我们提出了一种简单有效的方法，可以根据分类歧视评估伪标签的信心，并通过从高质量的伪标签中学习一致性，进一步完善本地化网络以获得更好的本地化性能。实验结果表明，我们提出的方法在三个基准数据集中实现了出色的性能，包括Cub-200-2011，Imagenet-1K和Tiny-Imagenet，这证明了其有效性。
Pseudo-supervised learning methods have been shown to be effective for weakly supervised object localization tasks. However, the effectiveness depends on the powerful regularization ability of deep neural networks. Based on the assumption that the localization network should have similar location predictions on different versions of the same image, we propose a two-stage approach to learn more consistent localization. In the first stage, we propose a mask-based pseudo label generator algorithm, and use the pseudo-supervised learning method to initialize an object localization network. In the second stage, we propose a simple and effective method for evaluating the confidence of pseudo-labels based on classification discrimination, and by learning consistency from high-quality pseudo-labels, we further refine the localization network to get better localization performance. Experimental results show that our proposed approach achieves excellent performance in three benchmark datasets including CUB-200-2011, ImageNet-1k and Tiny-ImageNet, which demonstrates its effectiveness.
