Multimodal Vision Research Laboratory

MVRL

Research Area: Astronomical Imagery and Data

We apply modern computer vision to astronomical surveys and cluster science, including transfer learning on SDSS multi-band images, self-supervised feature learning for cluster richness, and detection of inverse Compton emission. This thread demonstrates cross-domain use of representation learning methods developed in the lab.

View All Publications →

All Publications

  1. Lin S-C, Su Y, Gastaldello F, Jacobs N. 2024. Semisupervised Learning for Detecting Inverse Compton Emission in Galaxy Clusters. Astrophysical Journal 977:176. DOI: 10.3847/1538-4357/ad8888.
    paper doi bibtex Representation Learning
  2. Lin S-C, Su Y, Liang G, Zhang Y, Jacobs N, Zhang Y. 2022. Estimating Cluster Masses from SDSS Multi-band Images with Transfer Learning. Monthly Notices of the Royal Astronomical Society (MNRAS) 512:3885–3894. DOI: 10.1093/mnras/stac725.
    paper doi bibtex
  3. Zhang Y, Liang G, Su Y, Jacobs N. 2021. Multi-Branch Attention Networks for Classifying Galaxy Clusters. In: International Conference on Pattern Recognition (ICPR 2020). DOI: 10.1109/ICPR48806.2021.9412498.
    website doi bibtex
  4. Liang G, Su Y, Lin S-C, Zhang Y, Zhang Y, Jacobs N. 2020. Optical Wavelength Guided Self-Supervised Feature Learning For Galaxy Cluster Richness Estimate. In: Workshop on Machine Learning and the Physical Sciences at the 34th Conference on Neural Information Processing Systems.
    paper bibtex Representation Learning
  5. Su Y, Zhang Y, Liang G, ZuHone J, Barnes D, Jacobs N, Ntampaka M, Forman W, Nulsen P, Kraft R, Jones C. 2020. A deep learning view of the census of galaxy clusters in IllustrisTNG. Monthly Notices of the Royal Astronomical Society (MNRAS). DOI: 10.1093/mnras/staa2690.
    paper doi bibtex