论文标题
一袋用于分发概括的技巧
Bag of Tricks for Out-of-Distribution Generalization
论文作者
论文摘要
最近，分布（OOD）的概括引起了人们对基于深度学习模型的鲁棒性和概括能力的关注，因此，已经制定了许多策略来解决与该问题相关的不同方面。但是，大多数现有的OOD概括算法都是复杂的，并且专门为某些数据集设计。为了减轻此问题，Nicochallenge-2022提供了Nico ++，这是一个具有不同上下文信息的大规模数据集。在本文中，基于对NICO ++数据集的不同方案的系统分析，我们通过偶联的技巧袋提出了一个简单但有效的学习框架，包括多目标框架设计，数据增强，培训，培训和推理策略。我们的算法是记忆效率且易于安装的，没有复杂的模块，并且不需要大型预训练模型。它在公共测试集中的前1位精度为88.16％，在私人测试集中获得75.65％的表现，在域Nicochallenge-2022的域概括任务中排名第1。
Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue. However, most existing algorithms for OOD generalization are complicated and specifically designed for certain dataset. To alleviate this problem, nicochallenge-2022 provides NICO++, a large-scale dataset with diverse context information. In this paper, based on systematic analysis of different schemes on NICO++ dataset, we propose a simple but effective learning framework via coupling bag of tricks, including multi-objective framework design, data augmentations, training and inference strategies. Our algorithm is memory-efficient and easily-equipped, without complicated modules and does not require for large pre-trained models. It achieves an excellent performance with Top-1 accuracy of 88.16% on public test set and 75.65% on private test set, and ranks 1st in domain generalization task of nicochallenge-2022.
