语义分割是一项传统的任务，需要大量的像素级地面真实标签数据集，获取这些数据既费时又昂贵。最近在弱监督设置方面的进展表明，仅使用图像级别标签就可以获得合理的性能。分类通常作为训练深度神经网络的代理任务，从深度神经网络中提取注意力地图。然而，分类任务只需要最少的证据就可以进行预测，因此它关注的是识别性最强的目标区域。为了克服这个问题，我们提出了一种新的对抗擦除注意地图的方法。与以往的对抗擦除方法相比，我们优化了两个具有相反损耗函数的网络，消除了某些次优策略的要求;例如，有多个训练步骤使训练过程变得复杂，或者在运行于不同分布的网络之间的权重共享策略可能对性能不是最优的。该方法不需要显著性遮罩，而是利用正则化损失来防止注意力地图扩散到识别性较差的目标区域。我们在Pascal VOC数据集上的实验表明，我们的对抗方法比基准方法提高了分割性能2.1 mIoU，比以前的对抗擦除方法提高了1.0 mIoU。
原文题目：Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation
原文 ：Semantic segmentation is a task that traditionally requires a large dataset of pixel-level ground truth labels, which is time-consuming and expensive to obtain. Recent advancements in the weakly-supervised setting show that reasonable performance can be obtained by using only image-level labels. Classification is often used as a proxy task to train a deep neural network from which attention maps are extracted. However, the classification task needs only the minimum evidence to make predictions, hence it focuses on the most discriminative object regions. To overcome this problem, we propose a novel formulation of adversarial erasing of the attention maps. In contrast to previous adversarial erasing methods, we optimize two networks with opposing loss functions, which eliminates the requirement of certain suboptimal strategies; for instance, having multiple training steps that complicate the training process or a weight sharing policy between networks operating on different distributions that might be suboptimal for performance. The proposed solution does not require saliency masks, instead it uses a regularization loss to prevent the attention maps from spreading to less discriminative object regions. Our experiments on the Pascal VOC dataset demonstrate that our adversarial approach increases segmentation performance by 2.1 mIoU compared to our baseline and by 1.0 mIoU compared to previous adversarial erasing approaches.
如有侵权，请联系 firstname.lastname@example.org 删除。