A detection framework learns to rectify deviant visual features back to class-specific prototype anchors, improving generalization to unseen domains without target data.
Poda: Prompt-driven zero-shot domain adaptation,
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
-
Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection
A detection framework learns to rectify deviant visual features back to class-specific prototype anchors, improving generalization to unseen domains without target data.