2023/08/07 by Yingchi Liu, Liu, Yingchi, Zhu Liu +11
Computer Science · Engineering · Mathematics · #Advanced Image and Video Retrieval Techniques #Algorithm #Artificial intelligence #Bilevel optimization #Block (permutation group theory) #Code (set theory) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Domain (mathematical analysis) #Engineering #FOS: Computer and information sciences #Generalization #Generative Adversarial Networks and Image Synthesis #Generative grammar #Generative model #Machine learning #Mathematics #Optimization problem #Segmentation #Task (project management) #Visual Attention and Saliency Detection
paper · pdf · doi:10.48550/arxiv.2308.03381
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/08/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recently, there has been a growing interest in constructing deep learning schemes for Low-Light Vision (LLV). Existing techniques primarily focus on designing task-specific and data-dependent vision models on the standard RGB domain, which inherently contain latent data associations. In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain. This novel approach connects diverse vision problems by explicitly depicting data generation, which is the first in the field. To precisely characterize the latent correspondence between the generative procedure and the vision task, we establish a bilevel model with the parameters of the generative block defined as the upper level and the parameters of the vision task defined as the lower level. We further develop two types of learning strategies targeting different goals, namely low cost and high accuracy, to acquire a new bilevel generative learning paradigm. The generative blocks embrace a strong generalization ability in other low-light vision tasks through the bilevel optimization on enhancement tasks. Extensive experimental evaluations on three representative low-light vision tasks, namely enhancement, detection, and segmentation, fully demonstrate the superiority of our proposed approach. The code will be available at https://github.com/Yingchi1998/BGL.