A dual-stream network combining CNN and vision transformer features, followed by a rule extractor, achieves state-of-the-art accuracy on multiple Raven's Progressive Matrices benchmarks, including large gains on out-of-distribution PGM subsets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Visual Abstract Reasoning through Dual-Stream Networks
A dual-stream network combining CNN and vision transformer features, followed by a rule extractor, achieves state-of-the-art accuracy on multiple Raven's Progressive Matrices benchmarks, including large gains on out-of-distribution PGM subsets.