# Sanity Checks for Saliency Methods Explaining Object Detectors

arXiv: https://arxiv.org/abs/2306.02424 · HTML: https://mlsanity.com/paper/2306.02424/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 4 Jun 2023.

## Builds on (most cited first, 25 of 25)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [The (Un)reliability of saliency methods](https://mlsanity.com/paper/1711.00867/) (2017)
- [Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges](https://mlsanity.com/paper/1902.07830/) (2019)
- [Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond](https://mlsanity.com/paper/2202.06861/) (2022)
- [Sanity Checks for Saliency Metrics](https://mlsanity.com/paper/1912.01451/) (2019)
- [Black-box Explanation of Object Detectors via Saliency Maps](https://mlsanity.com/paper/2006.03204/) (2020)
- [Interpretability and Explainability: A Machine Learning Zoo Mini-tour](https://mlsanity.com/paper/2012.01805/) (2020)
- [Domain-adversarial neural networks to address the appearance variability of histopathology images](https://mlsanity.com/paper/1707.06183/) (2017)
- [Single Shot Text Detector with Regional Attention](https://mlsanity.com/paper/1709.00138/) (2017)
- [Revisiting Sanity Checks for Saliency Maps](https://mlsanity.com/paper/2110.14297/) (2021)
- [Sanity Simulations for Saliency Methods](https://mlsanity.com/paper/2105.06506/) (2021)
- [A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Survey](https://mlsanity.com/paper/2208.10895/) (2022)
- [Explain to Fix: A Framework to Interpret and Correct DNN Object Detector Predictions](https://mlsanity.com/paper/1811.08011/) (2018)
- [Deep Neural Networks for Marine Debris Detection in Sonar Images](https://mlsanity.com/paper/1905.05241/) (2019)
- [Perception for Autonomous Systems (PAZ)](https://mlsanity.com/paper/2010.14541/) (2020)
- [UOLO - automatic object detection and segmentation in biomedical images](https://mlsanity.com/paper/1810.05729/) (2018)

## Built on by (most cited first, 2 of 2)

- [Classification Metrics for Image Explanations: Towards Building Reliable XAI-Evaluations](https://mlsanity.com/paper/2406.05068/) (2024)
- [Explaining Object Detectors via Collective Contribution of Pixels](https://mlsanity.com/paper/2412.00666/) (2024)

## Abstract (arXiv)

Saliency methods are frequently used to explain Deep Neural Network-based models. Adebayo et al.'s work on evaluating saliency methods for classification models illustrate certain explanation methods fail the model and data randomization tests. However, on extending the tests for various state of the art object detectors we illustrate that the ability to explain a model is more dependent on the model itself than the explanation method. We perform sanity checks for object detection and define new qualitative criteria to evaluate the saliency explanations, both for object classification and bounding box decisions, using Guided Backpropagation, Integrated Gradients, and their Smoothgrad versions, together with Faster R-CNN, SSD, and EfficientDet-D0, trained on COCO. In addition, the sensitivity of the explanation method to model parameters and data labels varies class-wise motivating to perform the sanity checks for each class. We find that EfficientDet-D0 is the most interpretable method independent of the saliency method, which passes the sanity checks with little problems.