Adaptive Multiple-Attribute Scenario LoRA Merge for Robust Perception in Autonomous Driving

TL;DR

This paper introduces a new method to improve perception models in autonomous driving under rare weather and lighting conditions.

Contribution

The novel contribution is an adaptive framework using scenario-specific LoRA experts for robust perception in multiple-attribute conditions.

Findings

The proposed framework improves mIoU by up to 3.23 points in single-attribute settings.

In data-scarce multiple-attribute cases, merged LoRA experts outperform baselines by up to 5.99 points.

The method generalizes effectively across compounded environmental conditions.

Abstract

Perception models for autonomous driving are predominantly trained on clear, daytime data, leaving their performance under rare conditions—particularly in multiple-attribute (joint weather–lighting) conditions such as night × rainy or night × snowy—an open challenge. To address this, we propose a parameter-efficient fine-tuning (PEFT) framework that dynamically applies lightweight, scenario-specific Low-Rank Adaptation (LoRA) experts. At its core, our method features an adaptive pipeline that dynamically determines the LoRA experts to apply based on the encountered environmental conditions. We validate our framework on a unified semantic segmentation benchmark (MUSES, BDD100K, and Cityscapes) covering six scenarios (day/night × weather). Our approach improves the mIoU by up to 3.23 points over a strong baseline in single-attribute settings, and in data-scarce multiple-attribute cases, merged LoRA experts outperform the baseline expert by up to 5.99 points, demonstrating effective generalization across compounded conditions.

Figures