Training traffic sign classifiers with two frozen text-prototype losses, built from VLM-generated descriptions and class names, improves accuracy under shadows, natural light, and printed patches, with no inference-time overhead.
Robust physical-world attacks on deep learning visual classification,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles
Training traffic sign classifiers with two frozen text-prototype losses, built from VLM-generated descriptions and class names, improves accuracy under shadows, natural light, and printed patches, with no inference-time overhead.