Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2024

Abstract

Remote sensing (RS) imagery, requiring specialized satellites to collect and being difficult to annotate, suffers from data scarcity and class imbalance in certain spectrums. Due to data scarcity, training any large-scale RS models from scratch is unrealistic, and the alternative is to transfer pre-trained models by fine-tuning or a more data-efficient method LoRA. Due to class imbalance, transferred models exhibit strong bias, where features of the major class dominate over those of the minor class. In this paper, we propose debLoRA---a generic training approach that works with any LoRA variants to yield debiased features. It is an unsupervised learning approach that can diversify minor class features based on the shared attributes with major classes, where the attributes are obtained by a simple step of clustering.

Keywords

SAR, Remote-sensing images, LoRA, Visual transformers

Discipline

Categorical Data Analysis | Databases and Information Systems

Research Areas

Data Science and Engineering; Information Systems and Management

Publication

Proceedings of the 38th Conference on Neural Information Processing Systems, Vancouver, Canada, 2024 December 10-15

Publisher

The Neural Information Processing Systems Foundation

City or Country

California

Share

COinS