Representing Noisy Image Without Denoising

arXiv:2301.07409v2 Announce Type: replace
Abstract: A long-standing topic in artificial intelligence is the effective recognition of patterns from noisy images. In this regard, the recent data-driven paradigm considers 1) improving the representation robustness by adding noisy samples in training phase (i.e., data augmentation) or 2) pre-processing the noisy image by learning to solve the inverse problem (i.e., image denoising). However, such methods generally exhibit inefficient process and unstable result, limiting their practical applications. In this paper, we explore a non-learning …

abstract artificial artificial intelligence arxiv augmentation cs.cv data data-driven denoising eess.iv image images improving intelligence paradigm patterns pre-processing processing recognition regard representation robustness samples solve training type