DisINR improves INR medical reconstruction by disentangling shared and subject-specific representations, pre-training the shared modules from raw data via differentiable forward models, and freezing them at test time.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
RoMAE applies rotary positional embeddings to masked autoencoders to enable representation learning and interpolation on continuous positional data across irregular time-series, images, and audio without modality-specific modifications.
citing papers explorer
-
Disentangled Learning Improves Implicit Neural Representations for Medical Reconstruction
DisINR improves INR medical reconstruction by disentangling shared and subject-specific representations, pre-training the shared modules from raw data via differentiable forward models, and freezing them at test time.
-
Rotary Masked Autoencoders are Versatile Learners
RoMAE applies rotary positional embeddings to masked autoencoders to enable representation learning and interpolation on continuous positional data across irregular time-series, images, and audio without modality-specific modifications.