用对比学习自动学编码，让分类更抗对抗攻击
Contrastive ECOC: Learning Output Codes for Adversarial Defense
- 用对比学习自动生成纠错输出码，替代人工设计
- 在4个数据集上，对抗攻击下准确率提升显著
- 适合关注模型鲁棒性的研究者和工程应用
尽管一热编码常用于多分类任务，但并非最有效的编码方式。错误校正输出码（ECOC）通过将每个类别映射到唯一的码字作为标签来解决多分类问题。传统ECOC方法依赖手工设计或随机生成的码本，费时且结果可能不优、与数据集无关。本文提出三种基于对比学习的自动化码本学习模型，可直接从数据中自适应地学习码本。在四个数据集上，所提模型相比两种基线展现出更强的对抗攻击鲁棒性。代码已开源：https://github.com/YuChou20/Automated-Codebook-Learning-with-Error-Correcting-Output-Code-Technique。
原文摘要 · Abstract (English)
Although one-hot encoding is commonly used for multiclass classification, it is not always the most effective encoding mechanism. Error Correcting Output Codes (ECOC) address multiclass classification by mapping each class to a unique codeword used as a label. Traditional ECOC methods rely on manually designed or randomly generated codebooks, which are labor-intensive and may yield suboptimal, dataset-agnostic results. This paper introduces three models for automated codebook learning based on contrastive learning, allowing codebooks to be learned directly and adaptively from data. Across four datasets, our proposed models demonstrate superior robustness to adversarial attacks compared to two baselines. The source is available at https://github.com/YuChou20/Automated-Codebook-Learning-with-Error-Correcting-Output-Code-Technique.
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。