Overcoming Catastrophic Forgetting with Detail-Degradation Decoupling Networks for Super-Resolution
Abstract Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details. Existing methods are fine-tuned based on the application target during their usage, which enables them to be applied to new data domains. Neverthel...
Saved in:
Published in | Journal of physics. Conference series Vol. 2637; no. 1; pp. 12023 - 12029 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Bristol
IOP Publishing
01.11.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Abstract
Super-resolution reconstruction is a crucial technology that can significantly enhance image resolution and reconstruct high-frequency details. Existing methods are fine-tuned based on the application target during their usage, which enables them to be applied to new data domains. Nevertheless, the extent to which the fine-tuned model can generalize to the original data domain remains unclear, and therefore, additional research is warranted in this particular aspect. To solve the above problems, we analyzed the forgetting phenomenon of super-resolution methods under different degradation kernels, scenarios, and modalities. Then, we introduced Detail-Degradation Decoupling Networks, which separate the inverse process of degradation and the process of recovering high-frequency details in super-resolution. During the incremental learning process, the network parameters can be adjusted based on the task’s characteristics. Our experimental results demonstrate that our approach can significantly reduce catastrophic forgetting in super-resolution reconstruction and enhance the network’s ability to generalize and remain robust. |
---|---|
ISSN: | 1742-6588 1742-6596 |
DOI: | 10.1088/1742-6596/2637/1/012023 |