Label-Efficient Hyperspectral Image Classification via Spectral FiLM Modulation of Low-Level Pretrained Diffusion Features
This work addresses label-efficient classification for remote sensing applications, offering a domain-agnostic approach that is incremental in its use of existing diffusion models.
The paper tackles the problem of hyperspectral image classification with limited labeled data by leveraging pretrained diffusion model features and a spectral FiLM fusion module, achieving state-of-the-art performance on two datasets using only sparse annotations.
Hyperspectral imaging (HSI) enables detailed land cover classification, yet low spatial resolution and sparse annotations pose significant challenges. We present a label-efficient framework that leverages spatial features from a frozen diffusion model pretrained on natural images. Our approach extracts low-level representations from high-resolution decoder layers at early denoising timesteps, which transfer effectively to the low-texture structure of HSI. To integrate spectral and spatial information, we introduce a lightweight FiLM-based fusion module that adaptively modulates frozen spatial features using spectral cues, enabling robust multimodal learning under sparse supervision. Experiments on two recent hyperspectral datasets demonstrate that our method outperforms state-of-the-art approaches using only the provided sparse training labels. Ablation studies further highlight the benefits of diffusion-derived features and spectral-aware fusion. Overall, our results indicate that pretrained diffusion models can support domain-agnostic, label-efficient representation learning for remote sensing and broader scientific imaging tasks.