HGRL clusters states and objects into homogeneous groups via a GloVe co-occurrence graph and learns group-specific visual and prompt representations, improving compositional zero-shot recognition on three benchmarks.
A causal view of compositional zero-shot recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Transferable Homogeneous Groups for Compositional Zero-Shot Learning
HGRL clusters states and objects into homogeneous groups via a GloVe co-occurrence graph and learns group-specific visual and prompt representations, improving compositional zero-shot recognition on three benchmarks.