In Rain or Shine: Understanding and Overcoming Dataset Bias for Improving Robustness Against Weather Corruptions for Autonomous Vehicles

by   Aboli Marathe, et al.

Several popular computer vision (CV) datasets, specifically employed for Object Detection (OD) in autonomous driving tasks exhibit biases due to a range of factors including weather and lighting conditions. These biases may impair a model's generalizability, rendering it ineffective for OD in novel and unseen datasets. Especially, in autonomous driving, it may prove extremely high risk and unsafe for the vehicle and its surroundings. This work focuses on understanding these datasets better by identifying such "good-weather" bias. Methods to mitigate such bias which allows the OD models to perform better and improve the robustness are also demonstrated. A simple yet effective OD framework for studying bias mitigation is proposed. Using this framework, the performance on popular datasets is analyzed and a significant difference in model performance is observed. Additionally, a knowledge transfer technique and a synthetic image corruption technique are proposed to mitigate the identified bias. Finally, using the DAWN dataset, the findings are validated on the OD task, demonstrating the effectiveness of our techniques in mitigating real-world "good-weather" bias. The experiments show that the proposed techniques outperform baseline methods by averaged fourfold improvement.


page 3

page 4

page 5

page 6


Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditions

Segment Anything Model (SAM) has gained considerable interest in recent ...

Domain Adaptation based Enhanced Detection for Autonomous Driving in Foggy and Rainy Weather

Typically, object detection methods for autonomous driving that rely on ...

WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models

The open road poses many challenges to autonomous perception, including ...

Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images

For safety of autonomous driving, vehicles need to be able to drive unde...

Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias

With the swift advancement of deep learning, state-of-the-art algorithms...

AmodalSynthDrive: A Synthetic Amodal Perception Dataset for Autonomous Driving

Unlike humans, who can effortlessly estimate the entirety of objects eve...

Weather and Light Level Classification for Autonomous Driving: Dataset, Baseline and Active Learning

Autonomous driving is rapidly advancing, and Level 2 functions are becom...

Please sign up or login with your details

Forgot password? Click here to reset