Predicting Model Failure using Saliency Maps in Autonomous Driving Systems
While machine learning systems show high success rate in many complex tasks, research shows they can also fail in very unexpected situations. Rise of machine learning products in safety-critical industries cause an increase in attention in evaluating model robustness and estimating failure probability in machine learning systems. In this work, we propose a design to train a student model -- a failure predictor -- to predict the main model's error for input instances based on their saliency map. We implement and review the preliminary results of our failure predictor model on an autonomous vehicle steering control system as an example of safety-critical applications.
Code (1)
Tasks
Autonomous DrivingBIG-bench Machine LearningSteering ControlSimilar Papers 제목 키워드 기반
Two is Better Than One: Digital Siblings to Improve Autonomous Driving Testing
Simulation-based testing represents an important step to ensure the reliability of autonomous driving software. In practice, when companies rely on third-party general-purpose simulators, either for in-house or outsource…
Autonomous DrivingAutonomous VehiclesPolicy Distillation with Selective Input Gradient Regularization for Efficient Interpretability
Although deep Reinforcement Learning (RL) has proven successful in a wide range of tasks, one challenge it faces is interpretability when applied to real-world problems. Saliency maps are frequently used to provide inter…
Autonomous DrivingDeep Reinforcement LearningReinforcement Learning (RL)Visual Attention for Behavioral Cloning in Autonomous Driving
The goal of our work is to use visual attention to enhance autonomous driving performance. We present two methods of predicting visual attention maps. The first method is a supervised learning approach in which we collec…
Autonomous Driving"Looking at the Right Stuff" - Guided Semantic-Gaze for Autonomous Driving
In recent years, predicting driver's focus of attention has been a very active area of research in the autonomous driving community. Unfortunately, existing state-of-the-art techniques achieve this by relying only on hum…
Autonomous DrivingSaliency PredictionLooking at the right stuff: Guided semantic-gaze for autonomous driving
In recent years, predicting driver's focus of attention has been a very active area of research in the autonomous driving community. Unfortunately, existing state-of-the-art techniques achieve this by relying only on hum…
Autonomous DrivingSaliency Prediction