{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:10Z","timestamp":1778051470900,"version":"3.51.4"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00165","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1643-1652","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-Aware Subset Selection for Robust Visual Explainability under Distribution Shifts"],"prefix":"10.1109","author":[{"given":"Madhav","family":"Gupta","sequence":"first","affiliation":[{"name":"Indian Institute of Technology,Bombay,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vishak","family":"Prasad","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Bombay,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ganesh","family":"Ramakrishnan","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology,Bombay,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref2","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. Int. Conf. Machine Learning (ICML)","author":"Sundararajan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0314"},{"key":"ref4","article-title":"Less is more: Fewer interpretable regions via submodular subset selection","author":"Chen","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02796"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3028"},{"key":"ref7","article-title":"Metric-driven attributions for vision transformers","volume-title":"Proc. Int. Conf. Learning Representations (ICLR)","author":"Walker"},{"key":"ref8","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","author":"Simonyan","year":"2014"},{"key":"ref9","first-page":"9525","article-title":"Sanity checks for saliency maps","volume":"31","author":"Adebayo","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01657-x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_23"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3387702"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190679"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00391"},{"key":"ref17","article-title":"GdScore: Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift","author":"Xie","year":"2024"},{"key":"ref18","article-title":"Sensitivity and Generalization in Neural Networks: An Empirical Study","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Novak"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29270"},{"key":"ref20","article-title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","author":"Zhao","year":"2022"},{"key":"ref21","article-title":"Empirical failures of saliency maps across methods and metrics","volume-title":"ACML","author":"Zhang"},{"key":"ref22","first-page":"123","article-title":"Explainable Artificial Intelligence (XAI): Connecting artificial decision-making and human trust in autonomous vehicles","volume-title":"Proc. Third Int. Conf. on Computing, Communications, and Cyber-Security (IC4S)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref24","article-title":"Understanding Neural Networks Through Deep Visualization","volume-title":"Proc. Deep Learning Workshop","author":"Yosinski"},{"key":"ref25","first-page":"6076","article-title":"SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability","author":"Raghu","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref26","article-title":"Adversarial Weight Perturbation Helps Robust Generalization","volume-title":"International Conference on Learning Representations (ICLR)","author":"Wu"},{"key":"ref27","article-title":"Revisiting Random Weight Perturbation for Efficiently Improving Generalization","author":"Li","year":"2024","journal-title":"Transactions on Machine Learning Research (TMLR)"},{"key":"ref28","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"ICLR Workshop","author":"Hendrycks"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"ref30","first-page":"151","article-title":"RISE: Randomized Input Sampling for Explanation of Black-Box Models","volume-title":"Proc. British Machine Vision Conf. (BMVC)","author":"Petsiuk"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref32","article-title":"Exploring the limits of out-of-distribution detection","author":"Fort","year":"2021","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref34","article-title":"S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima","author":"Sung","year":"2020"},{"key":"ref35","article-title":"What \u2019Out-of-distribution\u2019 Is and Is Not","volume-title":"Proc. NeurIPS Workshop on Machine Learning Safety (ML Safety)","author":"Farquhar"},{"key":"ref36","first-page":"13153","article-title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Maddox"},{"key":"ref37","first-page":"13991","article-title":"Can You Trust Your Model\u2019s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Ovadia"},{"key":"ref38","first-page":"6402","article-title":"Simple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles","volume-title":"Proc. Advances in Neural Information Processing Systems (NeurIPS)","author":"Lakshminarayanan"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3321\/j.issn:0529-6579.2007.z1.029"},{"key":"ref40","first-page":"1823","article-title":"On the Connection Between Adversarial Robustness and Saliency Map Interpretability","volume-title":"Proc. Int. Conf. on Machine Learning (ICML)","author":"Etmann"},{"key":"ref41","article-title":"On the importance of gradients for detecting distributional shifts in the wild","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Huang","year":"2021"},{"key":"ref42","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Lee","year":"2018"},{"key":"ref43","article-title":"Understanding Softmax Confidence and Uncertainty","author":"Pearce"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492718.pdf?arnumber=11492718","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:13:02Z","timestamp":1778047982000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492718\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00165","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}