Frozen DINO features plus a 128-unit MLP on SegGPT-segmented eczema regions achieve weighted F1 0.67 in 4-class severity prediction, beating finetuned ResNet-18 and ViT-B on a 528-image in-the-wild dataset.
Journal of the European Academy of Dermatology and Venereology 29(12), 2417– 2422 (2015)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Automated Measurement of Eczema Severity with Self-Supervised Learning
Frozen DINO features plus a 128-unit MLP on SegGPT-segmented eczema regions achieve weighted F1 0.67 in 4-class severity prediction, beating finetuned ResNet-18 and ViT-B on a 528-image in-the-wild dataset.