SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving
This addresses reliability risks in safety-critical autonomous driving systems, representing an incremental improvement by focusing on robustness for existing models.
The paper tackled the problem of instability in deep learning models for accident anticipation in autonomous driving when faced with minor input perturbations, and introduced the SECURE framework that significantly enhances robustness and achieves new state-of-the-art results on clean data.
While deep learning has significantly advanced accident anticipation, the robustness of these safety-critical systems against real-world perturbations remains a major challenge. We reveal that state-of-the-art models like CRASH, despite their high performance, exhibit significant instability in predictions and latent representations when faced with minor input perturbations, posing serious reliability risks. To address this, we introduce SECURE - Stable Early Collision Understanding Robust Embeddings, a framework that formally defines and enforces model robustness. SECURE is founded on four key attributes: consistency and stability in both prediction space and latent feature space. We propose a principled training methodology that fine-tunes a baseline model using a multi-objective loss, which minimizes divergence from a reference model and penalizes sensitivity to adversarial perturbations. Experiments on DAD and CCD datasets demonstrate that our approach not only significantly enhances robustness against various perturbations but also improves performance on clean data, achieving new state-of-the-art results.