SHED improves domain generalization in CLIP by aligning style-homogenized embeddings instead of raw ones, achieving state-of-the-art results on five benchmarks including a 4% gain on DomainNet.
Advances in Neural Information Processing Systems , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.
citing papers explorer
-
SHED: Style-Homogenized Embedding Alignment for Domain Generalization
SHED improves domain generalization in CLIP by aligning style-homogenized embeddings instead of raw ones, achieving state-of-the-art results on five benchmarks including a 4% gain on DomainNet.
-
Beyond Instance-Level Self-Supervision in 3D Multi-Modal Medical Imaging
A self-supervised approach uses consistent spatial relationships of anatomical structures across patients to improve 3D multi-modal medical image representations, yielding modest gains on segmentation and classification tasks.