Distilling Vision-Language Models for Robust Traffic Sign Perception in Autonomous Vehicles

arXiv:2608.08815 · cs.LG · Submitted 2026-08-09 · Read on arXiv

Pedram MohajerAnsari, Amir Salarpour, Mert D. Pesé

cs.LG

Submitted: 2026-08-09

Updated: 2026-08-11

Comments: Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)

Code: https://github.com/pedram-mohajer/LAMDA

Project page: https://git-disl.github.io/GTDLBench/datasets

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 32× in this paper · explained in 1 episode
• Robustness — 26× in this paper · explained in 6 episodes
• Adversarial Examples — 12× in this paper · explained in 2 episodes
• Distillation — 10× in this paper · explained in 2 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Augmentation — 4× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Vision-language models — 4× in this paper · explained in 2 episodes
• Adversarial Robustness — 3× in this paper · explained in 4 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Transformers — 3× in this paper · explained in 2 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• Language-Anchored Model for Direction Alignment — 2× in this paper
• Regularization — 2× in this paper · explained in 3 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 10 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 14 episodes
• Georgia Tech Digital Intelligence Systems Laboratory — 1× in this paper
• Grounding — 1× in this paper · explained in 3 episodes
• Overfitting — 1× in this paper · explained in 2 episodes
• Scaling Laws — 1× in this paper · explained in 4 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Zeroth-Order Optimization — 1× in this paper · explained in 2 episodes

Sources

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Intriguing properties of neural networks
• Toward Inherently Robust VLMs Against Visual Perception Attacks
• Countering Adversarial Images using Input Transformations
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Robustness May Be at Odds with Accuracy
• NVILA: Efficient Frontier Visual Language Models
• Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Mitigating Adversarial Effects Through Randomization

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks