# A Programmatic and Semantic Approach to Explaining and DebuggingNeural Network Based Object Detectors

arXiv: https://arxiv.org/abs/1912.00289 · HTML: https://mlsanity.com/paper/1912.00289/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2019.

## Built on by (most cited first, 11 of 11)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation](https://mlsanity.com/paper/2110.14870/) (2021)
- [Active Assessment of Prediction Services as Accuracy Surface Over Attribute Combinations](https://mlsanity.com/paper/2108.06514/) (2021)
- [Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems](https://mlsanity.com/paper/2204.00480/) (2022)
- [Reachability analysis of neural networks using mixed monotonicity](https://mlsanity.com/paper/2111.07683/) (2021)
- [Querying Labelled Data with Scenario Programs for Sim-to-Real Validation](https://mlsanity.com/paper/2112.00206/) (2021)
- [TorchQL: A Programming Framework for Integrity Constraints in Machine Learning](https://mlsanity.com/paper/2308.06686/) (2023)
- [Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models](https://mlsanity.com/paper/2605.06640/) (2026)
- [Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching](https://mlsanity.com/paper/2110.05390/) (2021)
- [Reachability Analysis of Neural Networks with Uncertain Parameters](https://mlsanity.com/paper/2303.07917/) (2023)

## Abstract (arXiv)

Even as deep neural networks have become very effective for tasks in vision and perception, it remains difficult to explain and debug their behavior. In this paper, we present a programmatic and semantic approach to explaining, understanding, and debugging the correct and incorrect behaviors of a neural network-based perception system. Our approach is semantic in that it employs a high-level representation of the distribution of environment scenarios that the detector is intended to work on. It is programmatic in that scenario representation is a program in a domain-specific probabilistic programming language which can be used to generate synthetic data to test a given perception module. Our framework assesses the performance of a perception module to identify correct and incorrect detections, extracts rules from those results that semantically characterizes the correct and incorrect scenarios, and then specializes the probabilistic program with those rules in order to more precisely characterize the scenarios in which the perception module operates correctly or not. We demonstrate our results using the SCENIC probabilistic programming language and a neural network-based object detector. Our experiments show that it is possible to automatically generate compact rules that significantly increase the correct detection rate (or conversely the incorrect detection rate) of the network and can thus help with understanding and debugging its behavior.