arXiv · 2607.06305
Exploring Image-Text Alignment for Radio Galaxy Morphologies
Abstract
We investigate whether specially constructed text captions can capture the same morphological information as radio galaxy images. Using the MiraBest dataset, we generate captions with a domain-specific prompt and evaluate their alignment with images through the SigLIP-2 vision--language model, with and without LoRA fine-tuning. Results show that caption-based classification of FR-I and FR-II galaxies performs similarly to images, with fine-tuning improving local coherence of embeddings but not global alignment.
Explore related subjects
Keep this discovery
Erica Lastufka, Mariia Drozdova, Svyatoslav Volosynovskiy. 2026-07-07. Exploring Image-Text Alignment for Radio Galaxy Morphologies. https://arxiv.org/abs/2607.06305
Cite the original work for its findings. Save a collection to share your selection of sources.