A zero-shot multi-agent pipeline of ViLA, OmniVLM, GPT-4o-mini, and CLIP detects and describes novel road hazards, scoring 0.3922 on the authors' new COOOLER benchmark.
Aide: An automatic data engine for object detection in autonomous driving,
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
-
Towards a Multi-Agent Vision-Language System for Zero-Shot Novel Hazardous Object Detection for Autonomous Driving Safety
A zero-shot multi-agent pipeline of ViLA, OmniVLM, GPT-4o-mini, and CLIP detects and describes novel road hazards, scoring 0.3922 on the authors' new COOOLER benchmark.