# SE3D: A Framework For Saliency Method Evaluation In 3D Imaging

arXiv: https://arxiv.org/abs/2405.14584 · HTML: https://mlsanity.com/paper/2405.14584/

## Key facts

- Cited by 1 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 23 May 2024.

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

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge](https://mlsanity.com/paper/1811.02629/) (2018)
- [Unmasking Clever Hans Predictors and Assessing What Machines Really Learn](https://mlsanity.com/paper/1902.10178/) (2019)
- [Evaluating Weakly Supervised Object Localization Methods Right](https://mlsanity.com/paper/2001.07437/) (2020)
- [The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT](https://mlsanity.com/paper/2307.01984/) (2023)
- [Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks](https://mlsanity.com/paper/2011.08891/) (2020)
- [DeepLesion: Automated Deep Mining, Categorization and Detection of Significant Radiology Image Findings using Large-Scale Clinical Lesion Annotations](https://mlsanity.com/paper/1710.01766/) (2017)
- [An attempt at beating the 3D U-Net](https://mlsanity.com/paper/1908.02182/) (2019)
- [Saliency Tubes: Visual Explanations for Spatio-Temporal Convolutions](https://mlsanity.com/paper/1902.01078/) (2019)
- [MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning](https://mlsanity.com/paper/1910.09308/) (2019)
- [Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction](https://mlsanity.com/paper/2007.13224/) (2020)
- [Weakly Supervised Object Detection with 2D and 3D Regression Neural Networks](https://mlsanity.com/paper/1906.01891/) (2019)
- [Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification](https://mlsanity.com/paper/1803.02544/) (2018)
- [Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations](https://mlsanity.com/paper/1806.00102/) (2018)
- [Perception Visualization: Seeing Through the Eyes of a DNN](https://mlsanity.com/paper/2204.09920/) (2022)
- [Learning and Visualizing Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes](https://mlsanity.com/paper/1711.04851/) (2017)
- [XC: Exploring Quantitative Use Cases for Explanations in 3D Object Detection](https://mlsanity.com/paper/2210.11590/) (2022)

## Built on by (most cited first, 1 of 1)

- [Medical Slice Transformer: Improved Diagnosis and Explainability on 3D Medical Images with DINOv2](https://mlsanity.com/paper/2411.15802/) (2024)

## Abstract (arXiv)

For more than a decade, deep learning models have been dominating in various 2D imaging tasks. Their application is now extending to 3D imaging, with 3D Convolutional Neural Networks (3D CNNs) being able to process LIDAR, MRI, and CT scans, with significant implications for fields such as autonomous driving and medical imaging. In these critical settings, explaining the model's decisions is fundamental. Despite recent advances in Explainable Artificial Intelligence, however, little effort has been devoted to explaining 3D CNNs, and many works explain these models via inadequate extensions of 2D saliency methods. A fundamental limitation to the development of 3D saliency methods is the lack of a benchmark to quantitatively assess these on 3D data. To address this issue, we propose SE3D: a framework for Saliency method Evaluation in 3D imaging. We propose modifications to ShapeNet, ScanNet, and BraTS datasets, and evaluation metrics to assess saliency methods for 3D CNNs. We evaluate both state-of-the-art saliency methods designed for 3D data and extensions of popular 2D saliency methods to 3D. Our experiments show that 3D saliency methods do not provide explanations of sufficient quality, and that there is margin for future improvements and safer applications of 3D CNNs in critical fields.