用可解释算子分解识别任务，提升小样本下的鲁棒性。
Uncertainty-Aware Decomposed Hybrid Networks
- 将识别任务拆分为专注不同特征的专用算子
- 新置信度测量让模型优先可靠特征，降噪效果显著
- 适合数据少、需透明可靠的工业场景
图像识别模型的鲁棒性仍是关键挑战，现有模型常依赖大量标注数据。本文提出一种混合方法，结合神经网络的适应性与领域特定准不变算子的可解释性、透明性和鲁棒性。该方法将识别过程分解为多个针对特定任务的算子，聚焦不同特征，并引入一种专为这些算子设计的新置信度测量机制。该机制使网络能优先利用可靠特征并处理噪声。我们论证该设计提升了透明度和鲁棒性，尤其在低数据条件下性能更优。交通标志检测实验表明，该方法在半监督与无监督场景中均表现优异，凸显其在数据受限应用中的潜力。
原文摘要 · Abstract (English)
The robustness of image recognition algorithms remains a critical challenge, as current models often depend on large quantities of labeled data. In this paper, we propose a hybrid approach that combines the adaptability of neural networks with the interpretability, transparency, and robustness of domain-specific quasi-invariant operators. Our method decomposes the recognition into multiple task-specific operators that focus on different characteristics, supported by a novel confidence measurement tailored to these operators. This measurement enables the network to prioritize reliable features and accounts for noise. We argue that our design enhances transparency and robustness, leading to improved performance, particularly in low-data regimes. Experimental results in traffic sign detection highlight the effectiveness of the proposed method, especially in semi-supervised and unsupervised scenarios, underscoring its potential for data-constrained applications.
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。