# Failing to Learn: Autonomously Identifying Perception Failures for Self-driving Cars

arXiv: https://arxiv.org/abs/1707.00051 · HTML: https://mlsanity.com/paper/1707.00051/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2017.

## Built on by (most cited first, 28 of 28)

- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review](https://mlsanity.com/paper/2107.12045/) (2021)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)](https://mlsanity.com/paper/2302.13814/) (2023)
- [A Survey on Open Set Recognition](https://mlsanity.com/paper/2109.00893/) (2021)
- [Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes](https://mlsanity.com/paper/2109.09690/) (2021)
- [Fairness and Bias in Robot Learning](https://mlsanity.com/paper/2207.03444/) (2022)
- [Model-free Test Time Adaptation for Out-Of-Distribution Detection](https://mlsanity.com/paper/2311.16420/) (2023)
- [Rule-Based Error Detection and Correction to Operationalize Movement Trajectory Classification](https://mlsanity.com/paper/2308.14250/) (2023)
- [What's in the Black Box? The False Negative Mechanisms Inside Object Detectors](https://mlsanity.com/paper/2203.07662/) (2022)
- [Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge](https://mlsanity.com/paper/2407.15192/) (2024)
- [Run-time Introspection of 2D Object Detection in Automated Driving Systems Using Learning Representations](https://mlsanity.com/paper/2403.01172/) (2024)
- [Self-Aware Trajectory Prediction for Safe Autonomous Driving](https://mlsanity.com/paper/2305.09147/) (2023)
- [Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries](https://mlsanity.com/paper/2308.11189/) (2023)
- [Test & Evaluation Best Practices for Machine Learning-Enabled Systems](https://mlsanity.com/paper/2310.06800/) (2023)
- [XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees](https://mlsanity.com/paper/2104.10818/) (2021)
- [Run-time Monitoring of 3D Object Detection in Automated Driving Systems Using Early Layer Neural Activation Patterns](https://mlsanity.com/paper/2404.07685/) (2024)
- [Can We Ignore Labels In Out of Distribution Detection?](https://mlsanity.com/paper/2504.14704/) (2025)
- [Enhancing Your Trained DETRs with Box Refinement](https://mlsanity.com/paper/2307.11828/) (2023)
- [Evaluating Uncertainty Calibration for Open-Set Recognition](https://mlsanity.com/paper/2205.07160/) (2022)
- [CogSense: A Cognitively Inspired Framework for Perception Adaptation](https://mlsanity.com/paper/2107.10456/) (2021)
- [Preventing Errors in Person Detection: A Part-Based Self-Monitoring Framework](https://mlsanity.com/paper/2307.04533/) (2023)
- [Integrity Monitoring of 3D Object Detection in Automated Driving Systems using Raw Activation Patterns and Spatial Filtering](https://mlsanity.com/paper/2405.07600/) (2024)
- [Automated Trustworthiness Oracle Generation for Machine Learning Text Classifiers](https://mlsanity.com/paper/2410.22663/) (2024)
- [Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits](https://mlsanity.com/paper/2503.07020/) (2025)
- [Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference](https://mlsanity.com/paper/2602.06104/) (2026)
- [Position: Artificial Intelligence Needs Meta Intelligence -- the Case for Metacognitive AI](https://mlsanity.com/paper/2605.15567/) (2026)
- [LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated Driving](https://mlsanity.com/paper/2606.00372/) (2026)

## Abstract (arXiv)

One of the major open challenges in self-driving cars is the ability to detect cars and pedestrians to safely navigate in the world. Deep learning-based object detector approaches have enabled great advances in using camera imagery to detect and classify objects. But for a safety critical application, such as autonomous driving, the error rates of the current state of the art are still too high to enable safe operation. Moreover, the characterization of object detector performance is primarily limited to testing on prerecorded datasets. Errors that occur on novel data go undetected without additional human labels. In this letter, we propose an automated method to identify mistakes made by object detectors without ground truth labels. We show that inconsistencies in the object detector output between a pair of similar images can be used as hypotheses for false negatives (e.g., missed detections) and using a novel set of features for each hypothesis, an off-the-shelf binary classifier can be used to find valid errors. In particular, we study two distinct cues - temporal and stereo inconsistencies - using data that are readily available on most autonomous vehicles. Our method can be used with any camera-based object detector and we illustrate the technique on several sets of real world data. We show that a state-of-the-art detector, tracker, and our classifier trained only on synthetic data can identify valid errors on KITTI tracking dataset with an average precision of 0.94. We also release a new tracking dataset with 104 sequences totaling 80,655 labeled pairs of stereo images along with ground truth disparity from a game engine to facilitate further research. The dataset and code are available at https://fcav.engin.umich.edu/research/failing-to-learn