Label-Efficient Hyperspectral Image Classification via Spectral FiLM Modulation of Low-Level Pretrained Diffusion Features
By: Yuzhen Hu, Biplab Banerjee, Saurabh Prasad
Potential Business Impact:
Lets computers see details in satellite pictures.
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.
Similar Papers
Hyperspectral Imaging
CV and Pattern Recognition
Lets cameras see hidden details in everything.
SpectralTrain: A Universal Framework for Hyperspectral Image Classification
CV and Pattern Recognition
Trains computers to see Earth from space faster.
Uncertainty Quantification in HSI Reconstruction using Physics-Aware Diffusion Priors and Optics-Encoded Measurements
CV and Pattern Recognition
Makes blurry pictures of light colors sharp again.