mlsanityData to 14 Oct 2026

SMILE: A Super-resolution Guided Multi-task Learning Method for Hyperspectral Unmixing

arXiv 2509.11093 ↗First posted 14 Sep 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The performance of hyperspectral unmixing may be constrained by low spatial resolution, which can be enhanced using super-resolution in a multitask learning way. However, integrating super-resolution and unmixing directly may suffer two challenges: Task affinity is not verified, and the convergence of unmixing is not guaranteed. To address the above issues, in this paper, we provide theoretical analysis and propose super-resolution guided multi-task learning method for hyperspectral unmixing (SMILE). The provided theoretical analysis validates feasibility of multitask learning way and verifies task affinity, which consists of relationship and existence theorems by proving the positive guidance of super-resolution. The proposed framework generalizes positive information from super-resolution to unmixing by learning both shared and specific representations. Moreover, to guarantee the convergence, we provide the accessibility theorem by proving the optimal solution of unmixing. The major contributions of SMILE include providing progressive theoretical support, and designing a new framework for unmixing under the guidance of super-resolution. Our experiments on both synthetic and real datasets have substantiate the usefulness of our work.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 61 references that are in the map. First posted on arXiv 14 Sep 2025.

Builds on

17 of 61 references.

References · 17

  1. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  2. 2018An Augmented Linear Mixing Model to Address Spectral Variability for Hyperspectral Unmixingcited by 66
  3. 2023Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspectivecited by 51
  4. 2020Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolutioncited by 29
  5. 2021Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixingcited by 29
  6. 2015Hyperspectral unmixing with spectral variability using a perturbed linear mixing modelcited by 17
  7. 2014Nonlinear hyperspectral unmixing with robust nonnegative matrix factorizationcited by 16
  8. 2020A Plug-and-Play Priors Framework for Hyperspectral Unmixingcited by 13
  9. 2019Spectral Variability Aware Blind Hyperspectral Image Unmixing Based on Convex Geometrycited by 12
  10. 2015Robust Collaborative Nonnegative Matrix Factorization For Hyperspectral Unmixing (R-CoNMF)cited by 11
  11. 2022Entropic Descent Archetypal Analysis for Blind Hyperspectral Unmixingcited by 11
  12. 2023Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networkscited by 8
5 more
  1. 2017A Gaussian mixture model representation of endmember variability in hyperspectral unmixingcited by 7
  2. 2024Learning to Transfer for Evolutionary Multitaskingcited by 6
  3. 2020Illumination invariant hyperspectral image unmixing based on a digital surface modelcited by 4
  4. 2015A spatial compositional model (SCM) for linear unmixing and endmember uncertainty estimationcited by 2
  5. 2018Efficacy of regularized multi-task learning based on SVM modelscited by 1

Built on by

Not cited yet.