PARSE improves domain generalization accuracy by factoring recognition into visual primitives and their spatial relational compositions learned end-to-end with differentiable predicates.
Erm++: An improved baseline for domain generalization.arXiv preprint arXiv:2304.01973
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PAS estimates target accuracy for domain adaptation by measuring compatibility between source domains, pre-trained feature extractors, and target tasks using embeddings, correlating strongly with actual post-adaptation performance.
citing papers explorer
-
Domain Generalization through Spatial Relation Induction over Visual Primitives
PARSE improves domain generalization accuracy by factoring recognition into visual primitives and their spatial relational compositions learned end-to-end with differentiable predicates.
-
PAS: Estimating the target accuracy before domain adaptation
PAS estimates target accuracy for domain adaptation by measuring compatibility between source domains, pre-trained feature extractors, and target tasks using embeddings, correlating strongly with actual post-adaptation performance.