Kavli Affiliate: Jing Wang
| First 5 Authors: Wenxuan Wang, Jing Wang, Chen Chen, Jianbo Jiao, Yuanxiu Cai
| Summary:
The research community has witnessed the powerful potential of
self-supervised Masked Image Modeling (MIM), which enables the models capable
of learning visual representation from unlabeled data. In this paper, to
incorporate both the crucial global structural information and local details
for dense prediction tasks, we alter the perspective to the frequency domain
and present a new MIM-based framework named FreMIM for self-supervised
pre-training to better accomplish medical image segmentation tasks. Based on
the observations that the detailed structural information mainly lies in the
high-frequency components and the high-level semantics are abundant in the
low-frequency counterparts, we further incorporate multi-stage supervision to
guide the representation learning during the pre-training phase. Extensive
experiments on three benchmark datasets show the superior advantage of our
FreMIM over previous state-of-the-art MIM methods. Compared with various
baselines trained from scratch, our FreMIM could consistently bring
considerable improvements to model performance. The code will be publicly
available at https://github.com/Rubics-Xuan/FreMIM.
| Search Query: ArXiv Query: search_query=au:”Jing Wang”&id_list=&start=0&max_results=3