{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:16:48Z","timestamp":1774628208812,"version":"3.50.1"},"reference-count":17,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2023,6,28]],"date-time":"2023-06-28T00:00:00Z","timestamp":1687910400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Integrated gradients is an explainable AI technique that aims to explain the relationship between a model\u2019s predictions in terms of its features. Adapting this technique to point clouds and semantic segmentation models allows a class-wise attribution of the predictions with respect to the input features. This allows better insight into how a model reached a prediction. Furthermore, it allows a quantitative analysis of how much each feature contributes to a prediction. To obtain these attributions, a baseline with high entropy is generated and interpolated with the point cloud to be visualized. These interpolated point clouds are then run through the network and their gradients are collected. By observing the change in gradients during each iteration an attribution can be found for each input feature. These can then be projected back onto the original point cloud and compared to the predictions and input point cloud. These attributions are generated using RandLA-Net due to it being an efficient semantic segmentation model that uses comparatively few parameters, therefore keeping the number of gradients that must be stored at a reasonable level. The attribution was run on the public Semantic3D dataset and the SVGEO large-scale urban dataset.<\/jats:p>","DOI":"10.3390\/a16070316","type":"journal-article","created":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T01:15:47Z","timestamp":1688001347000},"page":"316","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Integrated Gradients for Feature Assessment in Point Cloud-Based Data Sets"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5190-670X","authenticated-orcid":false,"given":"Markus","family":"Schwegler","sequence":"first","affiliation":[{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"}]},{"given":"Christoph","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"},{"name":"Faculty of Digital Media, Furtwangen University, 78120 Furtwangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3196-3876","authenticated-orcid":false,"given":"Alexander","family":"Reiterer","sequence":"additional","affiliation":[{"name":"Fraunhofer Institute for Physical Measurement Techniques IPM, 79110 Freiburg, Germany"},{"name":"Department of Suistainable Systems Engnineering INATECH, Albert Ludwigs University Freiburg, 79110 Freiburg, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2023,6,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"97834","DOI":"10.1109\/ACCESS.2021.3094307","article-title":"Airborne LiDAR and Photogrammetric Point Cloud Fusion for Extraction of Urban Tree Metrics According to Street Network Segmentation","volume":"9","author":"Yang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/19479832.2016.1160960","article-title":"Advances in fusion of optical imagery and LiDAR point cloud applied to photogrammetry and remote sensing","volume":"8","author":"Zhang","year":"2017","journal-title":"Int. J. Image Data Fusion"},{"key":"ref_3","first-page":"1","article-title":"Individual Tree Crown Segmentation and Crown Width Extraction From a Heightmap Derived From Aerial Laser Scanning Data Using a Deep Learning Framework","volume":"13","author":"Sun","year":"2022","journal-title":"Front. Plant Sci."},{"key":"ref_4","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2016). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., and Solomon, J.M. (2018). Dynamic Graph CNN for Learning on Point Clouds. arXiv.","DOI":"10.1145\/3326362"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J., Marcotegui, B., Goulette, F., and Guibas, L.J. (2019). KPConv: Flexible and Deformable Convolution for Point Clouds. arXiv.","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., and Urtasun, R. (2019). PIXOR: Real-time 3D Object Detection from Point Clouds. arXiv.","DOI":"10.1109\/CVPR.2018.00798"},{"key":"ref_8","unstructured":"He, X., Zhao, K., and Chu, X. (2019). AutoML: A Survey of the State-of-the-Art. arXiv."},{"key":"ref_9","unstructured":"Devlin, J., Chang, M., Lee, K., and Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., and Markham, A. (2019). RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds. arXiv.","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Rusinkiewicz, S., and Levoy, M. (2000, January 23\u201328). QSplat: A Multiresolution Point Rendering System for Large Meshes. Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, New Orleans, LA, USA. SIGGRAPH \u201900.","DOI":"10.1145\/344779.344940"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kellner, M., Stahl, B., and Reiterer, A. (2022). Fused Projection-Based Point Cloud Segmentation. Sensors, 22.","DOI":"10.3390\/s22031139"},{"key":"ref_13","unstructured":"Zeng, W., and Gevers, T. (2017, January 22\u201329). 3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues. Proceedings of the European Conference on Computer Vision (ECCV) Workshops, Venice, Italy."},{"key":"ref_14","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: http:\/\/www.deeplearningbook.org."},{"key":"ref_15","unstructured":"Sundararajan, M., Taly, A., and Yan, Q. (2017). Axiomatic Attribution for Deep Networks. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liu, X., Deng, Z., and Yang, Y. (2018). Recent progress in semantic image segmentation. arXiv.","DOI":"10.1007\/s10462-018-9641-3"},{"key":"ref_17","unstructured":"Zalta, E.N. (2020). The Stanford Encyclopedia of Philosophy, Winter 2020 ed., Metaphysics Research Lab, Stanford University."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/7\/316\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:02:25Z","timestamp":1760126545000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/16\/7\/316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,28]]},"references-count":17,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["a16070316"],"URL":"https:\/\/doi.org\/10.3390\/a16070316","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,28]]}}}