DART combines a weakly supervised patch-refinement module with an LLM-derived class relationship graph to achieve state-of-the-art open-vocabulary multi-label recognition.
Title resolution pending
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
-
DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
DART combines a weakly supervised patch-refinement module with an LLM-derived class relationship graph to achieve state-of-the-art open-vocabulary multi-label recognition.