Jiang Weijie, Yu Yuanlong
College of Computer and Data Science, Fuzhou University, Fuzhou, China.
Front Neurorobot. 2022 Nov 3;16:1018383. doi: 10.3389/fnbot.2022.1018383. eCollection 2022.
While improving the performance on the out-of-distribution (OOD) benchmark dataset, the existing approach misses a portion of the valid discriminative information such that it reduces the performance on the same manifold OOD (SMOOD) data. The key to addressing this problem is to prompt the model to learn effective and comprehensive in-distribution (ID) semantic features. In this paper, two strategies are proposed to improve the generalization ability of the model to OOD data. Firstly, the original samples are replaced by features extracted from multiple "semantic perspectives" to obtain a comprehensive semantics of the samples; Second, the mean and variance of the batch samples are perturbed in the inference stage to improve the sensitivity of the model to the OOD data. The method we propose does not employ OOD samples, uses no pre-trained models in training, and does not require pre-processing of samples during inference. Experimental results show that our method enhances the semantic representation of ID data, surpasses state-of-the-art detection results on the OOD benchmark dataset, and significantly improves the performance of the model in detecting the SMOOD data.
在提高对分布外（OOD）基准数据集的性能时，现有方法遗漏了一部分有效的判别信息，从而降低了在相同流形分布外（SMOOD）数据上的性能。解决此问题的关键是促使模型学习有效且全面的分布内（ID）语义特征。本文提出了两种策略来提高模型对OOD数据的泛化能力。首先，用从多个“语义视角”提取的特征替换原始样本，以获得样本的综合语义；其次，在推理阶段对批次样本的均值和方差进行扰动，以提高模型对OOD数据的敏感性。我们提出的方法不使用OOD样本，在训练中不使用预训练模型，并且在推理过程中不需要对样本进行预处理。实验结果表明，我们的方法增强了ID数据的语义表示，在OOD基准数据集上超过了当前最优的检测结果，并显著提高了模型在检测SMOOD数据方面的性能。
