用变异关系自动重训练模型，提升图像识别鲁棒性。
Enhancing Deep Learning Model Robustness through Metamorphic Re-Training
- 通过变异关系生成新数据，结合半监督学习迭代重训练。
- 在多个数据集上平均提升17%的鲁棒性指标。
- 适合希望提升模型抗干扰能力的研究者和工程师。
本文评估了利用变异关系增强机器学习模型鲁棒性和实际表现的可行性。提出一种变异重训练框架，通过变异关系对数据进行变换，并采用半监督学习算法在迭代自适应的多轮过程中实现模型的自动化重训练、评估与测试。该框架集成FixMatch、FlexMatch、MixMatch和FullMatch等多种半监督重训练算法，支持指定配置下的模型优化。在CIFAR-10、CIFAR-100和MNIST数据集上，对多种预训练与非预训练图像模型进行了实验。结果表明，该方法显著提升了模型鲁棒性，所有模型在鲁棒性度量上平均额外提升了17个百分点。
原文摘要 · Abstract (English)
This paper evaluates the use of metamorphic relations to enhance the robustness and real-world performance of machine learning models. We propose a Metamorphic Retraining Framework, which applies metamorphic relations to data and utilizes semi-supervised learning algorithms in an iterative and adaptive multi-cycle process. The framework integrates multiple semi-supervised retraining algorithms, including FixMatch, FlexMatch, MixMatch, and FullMatch, to automate the retraining, evaluation, and testing of models with specified configurations. To assess the effectiveness of this approach, we conducted experiments on CIFAR-10, CIFAR-100, and MNIST datasets using a variety of image processing models, both pretrained and non-pretrained. Our results demonstrate the potential of metamorphic retraining to significantly improve model robustness as we show in our results that each model witnessed an increase of an additional flat 17 percent on average in our robustness metric.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。