# Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions

arXiv: https://arxiv.org/abs/1811.08011 · HTML: https://mlsanity.com/paper/1811.08011/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [Interpreting Object-level Foundation Models via Visual Precision Search](https://mlsanity.com/paper/2411.16198/) (2024)
- [Revealing Hidden Context Bias in Segmentation and Object Detection through Concept-specific Explanations](https://mlsanity.com/paper/2211.11426/) (2022)
- [Towards Better Explanations for Object Detection](https://mlsanity.com/paper/2306.02744/) (2023)
- [BSED: Baseline Shapley-Based Explainable Detector](https://mlsanity.com/paper/2308.07490/) (2023)
- [DExT: Detector Explanation Toolkit](https://mlsanity.com/paper/2212.11409/) (2022)
- [Sanity Checks for Saliency Methods Explaining Object Detectors](https://mlsanity.com/paper/2306.02424/) (2023)
- [PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution](https://mlsanity.com/paper/2606.18008/) (2026)
- [A Good Initialization is All You Need for Faithful Visual Attribution](https://mlsanity.com/paper/2607.06726/) (2026)

## Abstract (arXiv)

Explaining predictions of deep neural networks (DNNs) is an important and nontrivial task. In this paper, we propose a practical approach to interpret decisions made by a DNN object detector that has fidelity comparable to state-of-the-art methods and sufficient computational efficiency to process large datasets. Our method relies on recent theory and approximates Shapley feature importance values. We qualitatively and quantitatively show that the proposed explanation method can be used to find image features which cause failures in DNN object detection. The developed software tool combined into the "Explain to Fix" (E2X) framework has a factor of 10 higher computational efficiency than prior methods and can be used for cluster processing using graphics processing units (GPUs). Lastly, we propose a potential extension of the E2X framework where the discovered missing features can be added into training dataset to overcome failures after model retraining.