.png){kind=icon}
返回
Self-Parameter Distillation Dehazing
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2022.3231122.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we propose a novel dehazing method based on self-distillation. In contrast to conventional knowledge distillation approaches that transfer large models (teacher networks) to small models (student networks), we introduce a single knowledge distillation network that transfers network parameters to itself for dehazing. In the early stages, the proposed network transfers scene content (identity) information to the next stage of itself using haze-free data. However, in the later stages, the network transfers haze information to itself using haze data, enabling the accurate dehazing of input images using scene information from the early stages. In a single network, parameters are seamlessly updated from extracting global scene features to dehazing the scene. During the training, forward propagation acts as a teacher network, whereas backward propagation acts as a student network. The experimental results demonstrate that the proposed method considerably outperforms other state-of-the-art dehazing methods.
Keyword:
Knowledge engineering
Training
Task analysis
Atmospheric modeling
Feature extraction
Backpropagation
Deep learning
Dehazing
self-distillation
deraining
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
.png){kind=icon}
分享收藏
分享收藏Silver Contact Grid: Inferred Contact Resistivity and Cost Minimization in 19% Silicon Solar Cells
PREAI
分享收藏
查看更多内容