2022AAAI_Semantically Contrastive Learning for Low-light Image Enhancement(SCL_LLE)

1. motivation

利用语义对比学习

2. network

 (1) 输入的是低光图像首先经过图像增强的网络（Zero-DCE), 再将它传入语义分割网络中

（2）语义分割网络用的是DeepLabv3+

本栏目推荐文章
• LightGCL Simple Yet Effective Graph Contrastive Learning For Recommendation论文阅读笔记
• Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images
• Adaptive Graph Contrastive Learning for Recommendation论文阅读笔记
• Generative-Contrastive Graph Learning for Recommendation论文阅读笔记
• SAP ABAP 各种增强技术(Enhancement)概述 - 所谓第一代，第二代，第三代增强技术的出处试读版
• CA-TCC: 半监督时间序列分类的自监督对比表征学习《Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification》(时间序列、时序表征、时间和上下文对比、对比学习、自监督学习、半监督学习、TS-TCC的扩展版)
• 论文阅读13-SCGC:Simple Contrastive Graph Clustering
• 【略读论文|时序知识图谱补全】Temporal Knowledge Graph Reasoning with Historical Contrastive Learning
• 基于时间频率一致性对时间序列进行自监督对比预训练《Self-Supervised Contrastive Pre-Training for Time Series via Time-Frequency Consistency》(时序、时频一致性、对比学习)
• [论文阅读] Mean-Shifted Contrastive Loss for Anomaly Detection

AAAI_Semantically Semantically Contrastive Enhancement Low-lightaaai_semantically semantically contrastive enhancement aaai_semantically cvpr_snr-aware enhancement snr low-light cvpr_toward enhancement low-light flexible semantically low-light low-light light cvpr_learning instances enhancement cvpr_zero-reference enhancement estimation reference contrastive