论文标题
揭开无监督的语义对应估计
Demystifying Unsupervised Semantic Correspondence Estimation
论文作者
论文摘要
我们通过无监督学习的镜头探索语义对应估计。我们使用标准化的评估协议彻底评估了最近提出的几种跨多个挑战数据集的无监督方法，在该协议中，我们改变了诸如骨架体系结构，训练策略以及预训练和填充数据集等因素。为了更好地了解这些方法的故障模式，并为了提供更清晰的改进途径，我们提供了一个新的诊断框架以及一个新的性能指标，该指标更适合于语义匹配任务。最后，我们介绍了一种新的无监督对应方法，该方法利用了预训练的功能的强度，同时鼓励在训练过程中进行更好的比赛。与当前的最新方法相比，这会导致匹配性能明显更好。
We explore semantic correspondence estimation through the lens of unsupervised learning. We thoroughly evaluate several recently proposed unsupervised methods across multiple challenging datasets using a standardized evaluation protocol where we vary factors such as the backbone architecture, the pre-training strategy, and the pre-training and finetuning datasets. To better understand the failure modes of these methods, and in order to provide a clearer path for improvement, we provide a new diagnostic framework along with a new performance metric that is better suited to the semantic matching task. Finally, we introduce a new unsupervised correspondence approach which utilizes the strength of pre-trained features while encouraging better matches during training. This results in significantly better matching performance compared to current state-of-the-art methods.
