Cyclone intensity estimate with context-aware cyclegan
This work addresses data scarcity in cyclone intensity estimation for meteorology, but it is incremental as it builds on existing deep learning and GAN methods.
The paper tackles the problem of cyclone intensity estimation by addressing data scarcity for specific intensity classes, proposing a context-aware CycleGAN that synthesizes features for under-represented classes and achieves effectiveness in predicting unseen classes.
Deep learning approaches to cyclone intensity estimationhave recently shown promising results. However, sufferingfrom the extreme scarcity of cyclone data on specific in-tensity, most existing deep learning methods fail to achievesatisfactory performance on cyclone intensity estimation,especially on classes with few instances. To avoid the degra-dation of recognition performance caused by scarce samples,we propose a context-aware CycleGAN which learns the la-tent evolution features from adjacent cyclone intensity andsynthesizes CNN features of classes lacking samples fromunpaired source classes. Specifically, our approach synthe-sizes features conditioned on the learned evolution features,while the extra information is not required. Experimentalresults of several evaluation methods show the effectivenessof our approach, even can predicting unseen classes.