Distribution Modeling and GenAI-Assisted Projection for SAR Incremental Learning

Citation

Huang H, Gao F & Akbari V (2025) Distribution Modeling and GenAI-Assisted Projection for SAR Incremental Learning. In: BMVC 2025, Sheffield, 23.11.2025-27.11.2025. https://bmva-archive.org.uk/bmvc/2025/assets/workshops/MVEO/Paper_6/paper.pdf

Abstract
In class incremental learning for synthetic aperture radar (SAR) imagery, models must acquire new categories while retaining knowledge of previous ones. Generative replay can mitigate forgetting by synthesizing old class samples. However, vanilla gen-erative networks, such as variational autoencoder (VAE), prioritize pixel level reconstruction and do not inherently enforce class separability, which may not be optimal for incremental recognition. To address this issue, we analyze the distribution of the dataset used. The class-wise latent distributions are modeled via flow-based density estimation , enabling the generation of representative, in-distribution exemplars. Then we combine with current-task data, the exemplars support a feature projection between old and new latent spaces, from which a numerically optimized closed-form classifier is reconstructed. This dual use of learned distributions both constrains generative replay to in-distribution regions and calibrates decision boundaries to reduce drift. Experiments on SAR benchmarks demonstrate that our approach achieves state-of-the-art accuracy while maintaining a superior stability and plasticity trade-off.

Notes
HUANG ET. AL: SAR INCREMENTAL LEARNING 1