{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T03:02:25Z","timestamp":1779937345935,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T00:00:00Z","timestamp":1651190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,4,29]]},"DOI":"10.1145\/3491102.3517474","type":"proceedings-article","created":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T17:08:31Z","timestamp":1651165711000},"page":"1-16","source":"Crossref","is-referenced-by-count":15,"title":["How can Explainability Methods be Used to Support Bug Identification in Computer Vision Models?"],"prefix":"10.1145","author":[{"given":"Agathe","family":"Balayn","sequence":"first","affiliation":[{"name":"Software Technology, Delft University of Technology, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Natasa","family":"Rikalo","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph","family":"Lofi","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"Delft University of Technology, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Bozzon","sequence":"additional","affiliation":[{"name":"Web Information Systems, Delft University of Technology, Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,4,29]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"crossref","unstructured":"Ahmed Alqaraawi 2020. Evaluating saliency map explanations for convolutional neural networks: a user study. In IUI. 275\u2013285. Ahmed Alqaraawi 2020. Evaluating saliency map explanations for convolutional neural networks: a user study. In IUI. 275\u2013285.","DOI":"10.1145\/3377325.3377519"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702509"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445736"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/52.88939"},{"key":"e_1_3_2_2_6_1","unstructured":"Vijay Arya Rachel\u00a0KE Bellamy 2019. One explanation does not fit all: A toolkit and taxonomy of ai explainability techniques. (2019). Vijay Arya Rachel\u00a0KE Bellamy 2019. One explanation does not fit all: A toolkit and taxonomy of ai explainability techniques. (2019)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2700832"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450069"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278795"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"crossref","unstructured":"Umang Bhatt Alice Xiang 2020. Explainable machine learning in deployment. In FAT*. 648\u2013657. Umang Bhatt Alice Xiang 2020. Explainable machine learning in deployment. In FAT*. 648\u2013657.","DOI":"10.1145\/3351095.3375624"},{"key":"e_1_3_2_2_11_1","unstructured":"Shanqing Cai Eric Breck Eric Nielsen M Salib and D Sculley. 2016. Tensorflow debugger: Debugging dataflow graphs for machine learning. (2016). Shanqing Cai Eric Breck Eric Nielsen M Salib and D Sculley. 2016. Tensorflow debugger: Debugging dataflow graphs for machine learning. (2016)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Hao-Fei Cheng 2019. Explaining decision-making algorithms through UI: Strategies to help non-expert stakeholders. In CHI. 1\u201312. Hao-Fei Cheng 2019. Explaining decision-making algorithms through UI: Strategies to help non-expert stakeholders. In CHI. 1\u201312.","DOI":"10.1145\/3290605.3300789"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"crossref","unstructured":"Michael Chromik 2021. I Think I Get Your Point AI! The Illusion of Explanatory Depth in Explainable AI. In IUI. 307\u2013317. Michael Chromik 2021. I Think I Get Your Point AI! The Illusion of Explanatory Depth in Explainable AI. In IUI. 307\u2013317.","DOI":"10.1145\/3397481.3450644"},{"key":"e_1_3_2_2_14_1","unstructured":"A Ghorbani and al. 2019. Towards automatic concept-based explanations. In NeurIPS. A Ghorbani and al. 2019. Towards automatic concept-based explanations. In NeurIPS."},{"key":"e_1_3_2_2_15_1","unstructured":"Yash Goyal Ziyan Wu Jan Ernst Dhruv Batra Devi Parikh and Stefan Lee. 2019. Counterfactual visual explanations. In ICML. PMLR 2376\u20132384. Yash Goyal Ziyan Wu Jan Ernst Dhruv Batra Devi Parikh and Stefan Lee. 2019. Counterfactual visual explanations. In ICML. PMLR 2376\u20132384."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1147\/sj.411.0004"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Lisa\u00a0Anne Hendricks Kaylee Burns 2018. Women also snowboard: Overcoming bias in captioning models. In ECCV. 771\u2013787. Lisa\u00a0Anne Hendricks Kaylee Burns 2018. Women also snowboard: Overcoming bias in captioning models. In ECCV. 771\u2013787.","DOI":"10.1007\/978-3-030-01219-9_47"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Dan Hendrycks Steven Basart 2021. The many faces of robustness: A critical analysis of out-of-distribution generalization. In ICCV. 8340\u20138349. Dan Hendrycks Steven Basart 2021. The many faces of robustness: A critical analysis of out-of-distribution generalization. In ICCV. 8340\u20138349.","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"e_1_3_2_2_19_1","unstructured":"Dan Hendrycks and Thomas Dietterich. 2018. Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. In ICLR. Dan Hendrycks and Thomas Dietterich. 2018. Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. In ICLR."},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Fred Hohman 2019. Gamut: A design probe to understand how data scientists understand machine learning models. In CHI. 1\u201313. Fred Hohman 2019. Gamut: A design probe to understand how data scientists understand machine learning models. In CHI. 1\u201313.","DOI":"10.1145\/3290605.3300809"},{"key":"e_1_3_2_2_21_1","volume-title":"Summit: Scaling deep learning interpretability by visualizing activation and attribution summarizations","author":"Hohman Fred","year":"2019","unstructured":"Fred Hohman , Haekyu Park , Caleb Robinson , and Duen Horng\u00a0Polo Chau . 2019 . Summit: Scaling deep learning interpretability by visualizing activation and attribution summarizations . IEEE transactions on visualization and computer graphics 26, 1(2019), 1096\u20131106. Fred Hohman, Haekyu Park, Caleb Robinson, and Duen Horng\u00a0Polo Chau. 2019. Summit: Scaling deep learning interpretability by visualizing activation and attribution summarizations. IEEE transactions on visualization and computer graphics 26, 1(2019), 1096\u20131106."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Hilary Hutchinson Wendy Mackay 2003. Technology probes: inspiring design for and with families. In SIGCHI. 17\u201324. Hilary Hutchinson Wendy Mackay 2003. Technology probes: inspiring design for and with families. In SIGCHI. 17\u201324.","DOI":"10.1145\/642611.642616"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"S\u00e9rgio Jesus 2021. How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations. In FAccT. 805\u2013815. S\u00e9rgio Jesus 2021. How can I choose an explainer? An Application-grounded Evaluation of Post-hoc Explanations. In FAccT. 805\u2013815.","DOI":"10.1145\/3442188.3445941"},{"key":"e_1_3_2_2_24_1","volume-title":"NeurIPS MLSys Workshop.","author":"Kang Daniel","year":"2018","unstructured":"Daniel Kang , Deepti Raghavan , Peter Bailis , and Matei Zaharia . 2018 . Model assertions for debugging machine learning . In NeurIPS MLSys Workshop. Daniel Kang, Deepti Raghavan, Peter Bailis, and Matei Zaharia. 2018. Model assertions for debugging machine learning. In NeurIPS MLSys Workshop."},{"key":"e_1_3_2_2_25_1","unstructured":"Harmanpreet Kaur 2020. Interpreting Interpretability: Understanding Data Scientists\u2019 Use of Interpretability Tools for Machine Learning. In CHI. 1\u201314. Harmanpreet Kaur 2020. Interpreting Interpretability: Understanding Data Scientists\u2019 Use of Interpretability Tools for Machine Learning. In CHI. 1\u201314."},{"key":"e_1_3_2_2_26_1","volume-title":"Key challenges for delivering clinical impact with artificial intelligence. BMC medicine 17, 1","author":"Kelly J","year":"2019","unstructured":"Christopher\u00a0 J Kelly , Alan Karthikesalingam , Mustafa Suleyman , Greg Corrado , and Dominic King . 2019. Key challenges for delivering clinical impact with artificial intelligence. BMC medicine 17, 1 ( 2019 ), 1\u20139. Christopher\u00a0J Kelly, Alan Karthikesalingam, Mustafa Suleyman, Greg Corrado, and Dominic King. 2019. Key challenges for delivering clinical impact with artificial intelligence. BMC medicine 17, 1 (2019), 1\u20139."},{"key":"e_1_3_2_2_27_1","unstructured":"B Kim M Wattenberg and al. 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors. In ICML. B Kim M Wattenberg and al. 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors. In ICML."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM.2013.43"},{"key":"e_1_3_2_2_29_1","volume-title":"Repair: Removing representation bias by dataset resampling. In ICCV. 9572\u20139581.","author":"Li Yi","year":"2019","unstructured":"Yi Li and Nuno Vasconcelos . 2019 . Repair: Removing representation bias by dataset resampling. In ICCV. 9572\u20139581. Yi Li and Nuno Vasconcelos. 2019. Repair: Removing representation bias by dataset resampling. In ICCV. 9572\u20139581."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Q\u00a0Vera Liao 2020. Questioning the AI: informing design practices for explainable AI user experiences. In CHI. 1\u201315. Q\u00a0Vera Liao 2020. Questioning the AI: informing design practices for explainable AI user experiences. In CHI. 1\u201315.","DOI":"10.1145\/3313831.3376590"},{"key":"e_1_3_2_2_31_1","volume-title":"IUI Workshops.","author":"Lim Y","year":"2019","unstructured":"Brian\u00a0 Y Lim 2019 . Why these Explanations? Selecting Intelligibility Types for Explanation Goals .. In IUI Workshops. Brian\u00a0Y Lim 2019. Why these Explanations? Selecting Intelligibility Types for Explanation Goals.. In IUI Workshops."},{"key":"e_1_3_2_2_32_1","unstructured":"Anthony Liu Santiago Guerra 2020. Towards hybrid human-ai workflows for unknown unknown detection. In WWW. 2432\u20132442. Anthony Liu Santiago Guerra 2020. Towards hybrid human-ai workflows for unknown unknown detection. In WWW. 2432\u20132442."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3329486.3329489"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236082"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Shweta Narkar 2021. Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML. In IUI. 170\u2013174. Shweta Narkar 2021. Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML. In IUI. 170\u2013174.","DOI":"10.1145\/3397481.3450658"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00007"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2018.01.004"},{"key":"e_1_3_2_2_38_1","volume-title":"Proceedings of Machine Learning and Systems 3","author":"Rauschmayr Nathalie","year":"2021","unstructured":"Nathalie Rauschmayr , Vikas Kumar , Rahul Huilgol , Andrea Olgiati , Satadal Bhattacharjee , 2021 . Amazon SageMaker Debugger: A System for Real-Time Insights into Machine Learning Model Training . Proceedings of Machine Learning and Systems 3 (2021). Nathalie Rauschmayr, Vikas Kumar, Rahul Huilgol, Andrea Olgiati, Satadal Bhattacharjee, 2021. Amazon SageMaker Debugger: A System for Real-Time Insights into Machine Learning Model Training. Proceedings of Machine Learning and Systems 3 (2021)."},{"key":"e_1_3_2_2_39_1","volume-title":"Squares: Supporting interactive performance analysis for multiclass classifiers","author":"Ren Donghao","year":"2016","unstructured":"Donghao Ren , Saleema Amershi , Bongshin Lee , Jina Suh , and Jason\u00a0 D Williams . 2016 . Squares: Supporting interactive performance analysis for multiclass classifiers . IEEE transactions on visualization and computer graphics 23, 1(2016), 61\u201370. Donghao Ren, Saleema Amershi, Bongshin Lee, Jina Suh, and Jason\u00a0D Williams. 2016. Squares: Supporting interactive performance analysis for multiclass classifiers. IEEE transactions on visualization and computer graphics 23, 1(2016), 61\u201370."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Marco\u00a0Tulio Ribeiro 2016. Why should i trust you? Explaining the predictions of any classifier. In SIGKDD. 1135\u20131144. Marco\u00a0Tulio Ribeiro 2016. Why should i trust you? Explaining the predictions of any classifier. In SIGKDD. 1135\u20131144.","DOI":"10.18653\/v1\/N16-3020"},{"key":"e_1_3_2_2_41_1","volume-title":"Cockpit: A Practical Debugging Tool for Training Deep Neural Networks.","author":"Schneider Frank","year":"2021","unstructured":"Frank Schneider , Felix Dangel , and Philipp Hennig . 2021 . Cockpit: A Practical Debugging Tool for Training Deep Neural Networks. (2021). Frank Schneider, Felix Dangel, and Philipp Hennig. 2021. Cockpit: A Practical Debugging Tool for Training Deep Neural Networks. (2021)."},{"key":"e_1_3_2_2_42_1","volume-title":"UMLAUT: Debugging Deep Learning Programs using Program Structure and Model Behavior.","author":"Schoop E","year":"2021","unstructured":"E Schoop , F Huang , and B Hartmann . 2021 . UMLAUT: Debugging Deep Learning Programs using Program Structure and Model Behavior. (2021). E Schoop, F Huang, and B Hartmann. 2021. UMLAUT: Debugging Deep Learning Programs using Program Structure and Model Behavior. (2021)."},{"key":"e_1_3_2_2_43_1","unstructured":"K Simonyan A Vedaldi and A Zisserman. 2014. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. In ICLR. K Simonyan A Vedaldi and A Zisserman. 2014. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. In ICLR."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Sahil Singla Besmira Nushi S Shah E Kamar and E Horvitz. 2020. Understanding Failures of Deep Networks via Robust Feature Extraction. (2020). Sahil Singla Besmira Nushi S Shah E Kamar and E Horvitz. 2020. Understanding Failures of Deep Networks via Robust Feature Extraction. (2020).","DOI":"10.1109\/CVPR46437.2021.01266"},{"key":"e_1_3_2_2_45_1","unstructured":"D Smilkov and al. 2017. SmoothGrad: removing noise by adding noise. (2017). D Smilkov and al. 2017. SmoothGrad: removing noise by adding noise. (2017)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372870"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445088"},{"key":"e_1_3_2_2_48_1","volume-title":"Domain adaptation in computer vision applications","author":"Tommasi Tatiana","unstructured":"Tatiana Tommasi , Novi Patricia , Barbara Caputo , and Tinne Tuytelaars . 2017. A deeper look at dataset bias . In Domain adaptation in computer vision applications . Springer , 37\u201355. Tatiana Tommasi, Novi Patricia, Barbara Caputo, and Tinne Tuytelaars. 2017. A deeper look at dataset bias. In Domain adaptation in computer vision applications. Springer, 37\u201355."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"Anneliese von Mayrhauser and A\u00a0Marie Vans. 1997. Program understanding behavior during debugging of large scale software. In Papers presented at the seventh workshop on Empirical studies of programmers. 157\u2013179. Anneliese von Mayrhauser and A\u00a0Marie Vans. 1997. Program understanding behavior during debugging of large scale software. In Papers presented at the seventh workshop on Empirical studies of programmers. 157\u2013179.","DOI":"10.1145\/266399.266414"},{"key":"e_1_3_2_2_51_1","volume-title":"The what-if tool: Interactive probing of machine learning models","author":"Wexler James","year":"2019","unstructured":"James Wexler , Mahima Pushkarna , Tolga Bolukbasi , Martin Wattenberg , Fernanda Vi\u00e9gas , and Jimbo Wilson . 2019. The what-if tool: Interactive probing of machine learning models . IEEE transactions on visualization and computer graphics 26, 1( 2019 ), 56\u201365. James Wexler, Mahima Pushkarna, Tolga Bolukbasi, Martin Wattenberg, Fernanda Vi\u00e9gas, and Jimbo Wilson. 2019. The what-if tool: Interactive probing of machine learning models. IEEE transactions on visualization and computer graphics 26, 1(2019), 56\u201365."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Yao Xie 2020. CheXplain: Enabling Physicians to Explore and Understand Data-Driven AI-Enabled Medical Imaging Analysis. In CHI. 1\u201313. Yao Xie 2020. CheXplain: Enabling Physicians to Explore and Understand Data-Driven AI-Enabled Medical Imaging Analysis. In CHI. 1\u201313.","DOI":"10.1145\/3313831.3376807"},{"key":"e_1_3_2_2_53_1","volume-title":"Manifold: A model-agnostic framework for interpretation and diagnosis of machine learning models","author":"Zhang Jiawei","year":"2018","unstructured":"Jiawei Zhang , Yang Wang , Piero Molino , Lezhi Li , and David\u00a0 S Ebert . 2018 . Manifold: A model-agnostic framework for interpretation and diagnosis of machine learning models . IEEE transactions on visualization and computer graphics 25, 1(2018), 364\u2013373. Jiawei Zhang, Yang Wang, Piero Molino, Lezhi Li, and David\u00a0S Ebert. 2018. Manifold: A model-agnostic framework for interpretation and diagnosis of machine learning models. IEEE transactions on visualization and computer graphics 25, 1(2018), 364\u2013373."},{"key":"e_1_3_2_2_54_1","volume-title":"Machine learning testing: Survey, landscapes and horizons","author":"Zhang J\u00a0M","year":"2020","unstructured":"J\u00a0M Zhang , M Harman , and al. 2020. Machine learning testing: Survey, landscapes and horizons . IEEE Transactions on Software Engineering( 2020 ). J\u00a0M Zhang, M Harman, and al. 2020. Machine learning testing: Survey, landscapes and horizons. IEEE Transactions on Software Engineering(2020)."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"crossref","unstructured":"Peng Zhao Yu-Jie Zhang and Zhi-Hua Zhou. 2021. Exploratory machine learning with unknown unknowns. In AAAI Vol.\u00a035. 10999\u201311006. Peng Zhao Yu-Jie Zhang and Zhi-Hua Zhou. 2021. Exploratory machine learning with unknown unknowns. In AAAI Vol.\u00a035. 10999\u201311006.","DOI":"10.1609\/aaai.v35i12.17313"}],"event":{"name":"CHI '22: CHI Conference on Human Factors in Computing Systems","location":"New Orleans LA USA","acronym":"CHI '22","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3491102.3517474","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3491102.3517474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:11Z","timestamp":1750188671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3491102.3517474"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,29]]},"references-count":55,"alternative-id":["10.1145\/3491102.3517474","10.1145\/3491102"],"URL":"https:\/\/doi.org\/10.1145\/3491102.3517474","relation":{},"subject":[],"published":{"date-parts":[[2022,4,29]]}}}