BiCLIP recovers a structured geometric transformation from few-shot anchors to canonicalize domain features in VLMs and reports state-of-the-art results on 11 benchmarks.
Learning transferable visual models from natural language supervision, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
BiCLIP: Domain Canonicalization via Structured Geometric Transformation
BiCLIP recovers a structured geometric transformation from few-shot anchors to canonicalize domain features in VLMs and reports state-of-the-art results on 11 benchmarks.