A semantic-aware image-tabular pre-training method, using importance-guided masking and soft-label discretized reconstruction, sets new state-of-the-art results on dermatology and ophthalmology benchmarks.
In: European Con- ference on Computer Vision
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training
A semantic-aware image-tabular pre-training method, using importance-guided masking and soft-label discretized reconstruction, sets new state-of-the-art results on dermatology and ophthalmology benchmarks.