通过调控参数贡献模式，提升模型对异常输入的鲁棒性。
Shaping Parameter Contribution Patterns for Out-of-Distribution Detection
- 训练时动态调整高贡献参数，鼓励模型使用更广泛的参数决策
- 在多个数据集上显著降低OOD样本的过自信概率
- 适合需要可靠异常检测的工业部署场景
由于深度模型常产生过度自信的预测，分布外（OOD）检测面临挑战。本文揭示关键洞察：训练后的分类器往往依赖稀疏的参数贡献模式，即仅少数主导参数驱动预测。这种脆弱性可被异常输入利用，引发过自信输出。为此，我们提出一种简单有效的方法——参数贡献模式塑造（SPCP），通过在训练中基于动态阈值修正过高参数贡献，促使分类器学习边界导向的密集贡献模式。该机制使模型依赖更广泛的参数进行决策，从而降低因异常触发特定参数导致的过自信风险，同时保持分布内（ID）性能。大量实验验证了SPCP在多种OOD检测设置下的有效性。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) detection is a well-known challenge due to deep models often producing overconfident. In this paper, we reveal a key insight that trained classifiers tend to rely on sparse parameter contribution patterns, meaning that only a few dominant parameters drive predictions. This brittleness can be exploited by OOD inputs that anomalously trigger these parameters, resulting in overconfident predictions. To address this issue, we propose a simple yet effective method called Shaping Parameter Contribution Patterns (SPCP), which enhances OOD detection robustness by encouraging the classifier to learn boundary-oriented dense contribution patterns. Specifically, SPCP operates during training by rectifying excessively high parameter contributions based on a dynamically estimated threshold. This mechanism promotes the classifier to rely on a broader set of parameters for decision-making, thereby reducing the risk of overconfident predictions caused by anomalously triggered parameters, while preserving in-distribution (ID) performance. Extensive experiments under various OOD detection setups verify the effectiveness of SPCP.
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。