论文标题
从损失景观角度来看的引导概括能力
Bootstrap Generalization Ability from Loss Landscape Perspective
论文作者
论文摘要
域的概括旨在学习一个可以很好地概括在看不见的测试数据集（即分布数据集）上的模型，该模型与培训数据集不同。为了解决计算机视觉中的领域概括，我们将损失景观理论引入该领域。具体来说，我们从损失景观的角度来启动深度学习模型的概括能力，包括骨干，正则化，训练范式和学习率。我们通过进行广泛的消融研究和可视化来验证有关NICO ++，PAC和VLCS数据集的提出理论。此外，我们将该理论应用于ECCV 2022 NICO挑战1，并在不使用任何域不变方法的情况下获得第三名。
Domain generalization aims to learn a model that can generalize well on the unseen test dataset, i.e., out-of-distribution data, which has different distribution from the training dataset. To address domain generalization in computer vision, we introduce the loss landscape theory into this field. Specifically, we bootstrap the generalization ability of the deep learning model from the loss landscape perspective in four aspects, including backbone, regularization, training paradigm, and learning rate. We verify the proposed theory on the NICO++, PACS, and VLCS datasets by doing extensive ablation studies as well as visualizations. In addition, we apply this theory in the ECCV 2022 NICO Challenge1 and achieve the 3rd place without using any domain invariant methods.
