| Summary: | During the past decades, the invention and employment of multiple sensors have enabled multisensor remote-sensing images (RSIs) image acquisition. In order to effectively use these images for RS scene understanding, a scene classification model trained with samples collected from one sensor should generalize well to other sensors. However, it is extremely challenging to directly transfer between different sensors. The key reason is that: If we regard the images obtained by different sensors as the data distributed in different domains, there are large interdomain gaps caused by multiple factors like image scene contents and sensor imaging parameters. To address this, we proposed a general transitive transfer learning (TTL) framework for cross-optical RSIs scene understanding, which can be easily coupled with most of the existing transfer learning methods. The core idea is to gradually minimize the interdomain gap between different sensors by several intermediate domains, which are constructed by a single-factor criterion that only one factor is changed between adjacent domains. Then one challenging cross-optical sensor scene understanding task can be divided into several easier subtasks connected by these intermediate domains (source domain <inline-formula><tex-math notation="LaTeX">$\rightarrow$</tex-math></inline-formula> 1st intermediate domain <inline-formula><tex-math notation="LaTeX">$\rightarrow $</tex-math></inline-formula> 2nd intermediate domain <inline-formula><tex-math notation="LaTeX">$\rightarrow \dots \rightarrow$</tex-math></inline-formula> target domain). Each subtask can be regarded as a direct-transfer task, and can be completed using a mainstream transfer learning method. Experiments using six sets of cross-optical sensor RSIs datasets demonstrated that the framework can fit most transfer learning methods and improve their performance. Our framework achieves a new state-of-the-art compared to recently published transfer learning methods.
|
|---|