A PARAMETER-EFFICIENT DIFFERENTIABLE ACTIVE CONTOUR NETWORK FOR PRECISELY BUILDING INSTANCE SEGMENTATION
Published in IEEE International Geoscience and Remote Sensing Symposium, 2024
This paper proposes a PDAC network that uses adapter fine-tuning encoders instead of training from scratch, coupling DNN and ACM with a very small number of parameters to achieve end-to-end building segmentation. On two major building datasets, the effectiveness of the parameter efficient fine-tuning method was verified by achieving better performance than the baseline with nearly half of the computing resources.
Recommended citation:
Z. Zhu, B. Dong, Q. Bu and J. Ni, "A Parameter-Efficient Differentiable Active Contour Network for Precisely Building Instance Segmentation," IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 8355-8359, doi: 10.1109/IGARSS53475.2024.10642815.
Download Paper