通过输入变换与重采样，降低模型推理中的认知不确定性。
Invariant Transformation and Resampling based Epistemic-Uncertainty Reduction
- 对输入做不变变换后多次推理，利用误差的不相关性提升结果
- 可显著减少认知不确定性带来的错误，提升推理准确率
- 适合追求高精度且资源有限的部署场景
人工智能模型可视为高维空间中将输入映射到输出的函数。模型设计并训练完成后用于推理，但即使优化良好的模型仍可能因随机不确定性和认知不确定性产生误差。我们观察到，对同一输入进行不变变换后多次推理时，推理误差在一定程度上呈现独立性，这源于认知不确定性。基于此，我们提出一种基于重采样的推理方法：对训练好的模型使用输入的多个变换版本进行推理，并聚合输出以获得更准确的结果。该方法有望提高推理准确性，为模型大小与性能之间的权衡提供新策略。
原文摘要 · Abstract (English)
An artificial intelligence (AI) model can be viewed as a function that maps inputs to outputs in high-dimensional spaces. Once designed and well trained, the AI model is applied for inference. However, even optimized AI models can produce inference errors due to aleatoric and epistemic uncertainties. Interestingly, we observed that when inferring multiple samples based on invariant transformations of an input, inference errors can show partial independences due to epistemic uncertainty. Leveraging this insight, we propose a "resampling" based inferencing that applies to a trained AI model with multiple transformed versions of an input, and aggregates inference outputs to a more accurate result. This approach has the potential to improve inference accuracy and offers a strategy for balancing model size and performance.
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。