论文标题
通过顺序对抗掩蔽改善自我监督的表示学习
Improving self-supervised representation learning via sequential adversarial masking
论文作者
论文摘要
自我监督学习中的最新方法表明，基于掩盖的借口任务超出了NLP，可以作为计算机视觉中有用的预处理目标。但是，现有方法采用随机或临时掩盖策略，限制了重建任务的难度，因此是学习表示的强度。我们通过提出一个新的框架来以依次的方式生成面具，从而改善学习对抗面具的最新工作，并在对手身上具有不同的约束。这导致了各种下游任务的性能改善，例如Imagenet100，STL10和CIFAR10/100的分类以及Pascal VOC的分割。我们的结果进一步证明了计算机视觉中SSL的基于掩盖的方法的有希望的功能。
Recent methods in self-supervised learning have demonstrated that masking-based pretext tasks extend beyond NLP, serving as useful pretraining objectives in computer vision. However, existing approaches apply random or ad hoc masking strategies that limit the difficulty of the reconstruction task and, consequently, the strength of the learnt representations. We improve upon current state-of-the-art work in learning adversarial masks by proposing a new framework that generates masks in a sequential fashion with different constraints on the adversary. This leads to improvements in performance on various downstream tasks, such as classification on ImageNet100, STL10, and CIFAR10/100 and segmentation on Pascal VOC. Our results further demonstrate the promising capabilities of masking-based approaches for SSL in computer vision.
