SignReasoner decomposes traffic signs into functional structure units and uses a two-stage VLM post-training pipeline to achieve state-of-the-art compositional reasoning on a new benchmark.
A survey of deep learning techniques for autonomous driving.Journal of Field Robotics, 37(3):362– 386
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SignReasoner: Compositional Reasoning for Complex Traffic Sign Understanding via Functional Structure Units
SignReasoner decomposes traffic signs into functional structure units and uses a two-stage VLM post-training pipeline to achieve state-of-the-art compositional reasoning on a new benchmark.