MDFL: Multi-Domain Diffusion-Driven Feature Learning
DOI:
https://doi.org/10.1609/aaai.v38i8.28710Keywords:
DMKM: Mining of Visual, Multimedia & Multimodal Data, CV: Object Detection & Categorization, CV: Scene Analysis & Understanding, ML: Feature Construction/ReformulationAbstract
High-dimensional images, known for their rich semantic information, are widely applied in remote sensing and other fields. The spatial information in these images reflects the object's texture features, while the spectral information reveals the potential spectral representations across different bands. Currently, the understanding of high-dimensional images remains limited to a single-domain perspective with performance degradation. Motivated by the masking texture effect observed in the human visual system, we present a multi-domain diffusion-driven feature learning network (MDFL) , a scheme to redefine the effective information domain that the model really focuses on. This method employs diffusion-based posterior sampling to explicitly consider joint information interactions between the high-dimensional manifold structures in the spectral, spatial, and frequency domains, thereby eliminating the influence of masking texture effects in visual models. Additionally, we introduce a feature reuse mechanism to gather deep and raw features of high-dimensional data. We demonstrate that MDFL significantly improves the feature extraction performance of high-dimensional data, thereby providing a powerful aid for revealing the intrinsic patterns and structures of such data. The experimental results on three multi-modal remote sensing datasets show that MDFL reaches an average overall accuracy of 98.25%, outperforming various state-of-the-art baseline schemes. Code available at https://github.com/LDXDU/MDFL-AAAI-24.Downloads
Published
2024-03-24
How to Cite
Li, D., Xie, W., Zhang, J., & Li, Y. (2024). MDFL: Multi-Domain Diffusion-Driven Feature Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 8653-8660. https://doi.org/10.1609/aaai.v38i8.28710
Issue
Section
AAAI Technical Track on Data Mining & Knowledge Management