Multiple Task-Oriented Encoders for Unified Image Fusion

Zhuoxiao Li, Jinyuan Liu, Risheng Liu, Xin Fan, Zhongxuan Luo, Wen GaoICME 2021 · OpenReview

Abstract

Image fusion methods have achieved incredible progress, but they are vulnerable to handling a certain type of fusion task rather than considering deeper relations between cross-realm task correlations. To achieve this, we integrate different image fusion tasks into a unified network. Our method is accomplished through multiple task-oriented encoders and a generic decoder, in addition to a self-adapting loss function. The taskoriented encoders are trained to learn task-specific features, while the generic decoder reconstructs the fused features to generate a comprehensive image. Subsequently, by introducing the self-adapting loss in our method, it can automatically adjust itself to source data characteristics on different tasks. Besides, we formulate a training strategy based on bilevel optimization to update the multi-encoder and generic decoder in an alternative manner. Extensive experimental results demonstrate the superior performance of our method over the stateof-the-art methods.
BibTeX
@inproceedings{li2021multiple,
  author = {Zhuoxiao Li and Jinyuan Liu and Risheng Liu and Xin Fan and Zhongxuan Luo and Wen Gao},
  title = {{Multiple Task-Oriented Encoders for Unified Image Fusion}},
  booktitle = {ICME},
  year = {2021},
  url = {https://openreview.net/forum?id=St1am-paSHh},
}

Loading related content...

Figure