RF-DETR trained on ELAIS-N1 achieves ~91% F1 for detection and morphology classification on LOFAR images, generalizes to other fields, recovers most PyBDSF sources as single entities rather than fragmented components, flags artefacts, and matches visual IDs of extended galaxies.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
MIDOG 2025 challenge shows top mitosis detection F1 of 0.740 and atypical figure balanced accuracy of 0.908 across diverse tumors, with clear drops in challenging regions and tumor-type variation.
citing papers explorer
-
Transformer-Based Source Detection and Morphological Classification in LOFAR Deep-Field Continuum Images
RF-DETR trained on ELAIS-N1 achieves ~91% F1 for detection and morphology classification on LOFAR images, generalizes to other fields, recovers most PyBDSF sources as single entities rather than fragmented components, flags artefacts, and matches visual IDs of extended galaxies.