Recent supervised and unsupervised image representation learning algorithms have achieved quantum leaps. However, these techniques do not account for representation resilience against noise in their design paradigms. Consequently, these effective methods suffer failure when confronted with noise outside the training distribution, such as complicated real-world noise that is usually opaque to model training. To address this issue, dual domains are optimized to separately model a canonical space for noisy representations, namely the Noise-Robust (NR) domain, and a twinned canonical clean space, namely the Noise-Free (NF) domain, by maximizing the interaction information between the representations. Given the dual canonical domains, we design a target-guided implicit neural mapping function to accurately translate the NR representations to the NF domain, yielding noise-resistant representations by eliminating noise regencies. The proposed method is a scalable module that can be readily integrated into existing learning systems to improve their robustness against noise. Comprehensive trials of various tasks using both synthetic and real-world noisy data demonstrate that the proposed Target-Guided Dual-Domain Translation (TDDT) method is able to achieve remarkable performance and robustness in the face of complex noisy images.

翻译：近期有监督与无监督图像表示学习算法取得了显著突破。然而，这些技术在设计范式中并未考虑对噪声的表示韧性。因此，当面对训练分布外的噪声（例如通常对模型训练不透明的复杂真实世界噪声）时，这些有效方法会出现失效。为解决此问题，通过最大化表示之间的交互信息，双域被优化以分别为噪声表示（即噪声鲁棒域，NR域）和对应的干净空间（即无噪声域，NF域）建立正则化空间。基于双正则化域，我们设计了一种目标引导的隐式神经映射函数，将NR表示精确转换至NF域，通过消除噪声残留获得抗噪声表示。所提方法作为一种可扩展模块，可轻松集成至现有学习系统以增强其噪声鲁棒性。使用合成与真实噪声数据进行的多任务综合实验表明，所提出的目标引导双域翻译（TDDT）方法在面对复杂噪声图像时能够实现卓越性能与鲁棒性。