用低秩适配器统一检测分布外数据的分类失败，提升模型可靠性。
TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data
- 通过低秩适配器分离并整合故障特异性可靠性知识
- 在多种分布外场景下显著提升拒识能力
- 适合需要安全决策的开放环境部署
深度神经网络在开放环境中部署时，需应对协变量和语义分布外（OOD）数据的自然出现。可靠预测要求模型正确识别正常输入，同时拒绝误分类的协变量偏移和语义偏移样本。考虑到不同类型失败案例间的拒识权衡，亟需更便捷、可控且灵活的故障检测方法。为此，本文提出一种简单统一的分类拒识框架，通过分离并整合基于低秩适配器的故障特异性可靠性知识，有效增强检测能力。大量实验表明该框架在多种分布外场景下均表现优越。
原文摘要 · Abstract (English)
Reliable prediction is an essential requirement for deep neural models that are deployed in open environments, where both covariate and semantic out-of-distribution (OOD) data arise naturally. In practice, to make safe decisions, a reliable model should accept correctly recognized inputs while rejecting both those misclassified covariate-shifted and semantic-shifted examples. Besides, considering the potential existing trade-off between rejecting different failure cases, more convenient, controllable, and flexible failure detection approaches are needed. To meet the above requirements, we propose a simple failure detection framework to unify and facilitate classification with rejection under both covariate and semantic shifts. Our key insight is that by separating and consolidating failure-specific reliability knowledge with low-rank adapters and then integrating them, we can enhance the failure detection ability effectively and flexibly. Extensive experiments demonstrate the superiority of our framework.
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。