Computer Vision News - January 2024

Computer Vision News 22 Deep Learning for the Eyes by Christina Bornberg @datascEYEnce Hello everyone! I am Christina and as every month, I am happy to share another datascEYEnce story with you! I hope you all had a good start to the new year and are ready to learn about Lehan’s work on multimodal image classification using fundus images to increase the accuracy of OCT classification! This interview is very special to me because it marks the first in-person interview I did for the column! featuring Lehan Wang Lehan completed her undergraduate degree in computer science before becoming an intern and later starting her PhD under the supervision of Xiaomeng Li at the Hong Kong University of Science and Technology (HKUST). She was able to present her work “Fundus-Enhanced Disease-Aware Distillation Model for Retinal Disease Classification from OCT Images” at MICCAI 2023. This is also the subject of the interview with her. Knowledge distillation for multi-modal retinal images Now, let's delve into Lehan's journey in deep learning for ophthalmology, which actually didn’t start in the vision field, but in NLP. She has been working alongside a brilliant PhD student during her undergrad who taught her more about deep learning and research in general, as well as helped with suggestions for career planning. She ended up choosing HKUST where she had two possible topic options: multi-modal image analysis and image registration. Due to her interest in image fusion and multi-modality, she decided to go with the first option.