A diffusion-transformer segmentation model with rectified flow claims state-of-the-art skin lesion results, but its own table shows it does not lead on at least one dataset.
IEEE Transactions on Pattern Analysis and Machine Intelli- gence 40(4), 834–848 (2018)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
SegDT: A Diffusion Transformer-Based Segmentation Model for Medical Imaging
A diffusion-transformer segmentation model with rectified flow claims state-of-the-art skin lesion results, but its own table shows it does not lead on at least one dataset.