{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:24Z","timestamp":1763191704615,"version":"3.45.0"},"reference-count":75,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227842","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Interpretability-Aware Vision Transformer"],"prefix":"10.1109","author":[{"given":"Yao","family":"Qiang","sequence":"first","affiliation":[{"name":"Wayne State University,Computer Science Department,Detroit,USA"}]},{"given":"Chengyin","family":"Li","sequence":"additional","affiliation":[{"name":"Wayne State University,Computer Science Department,Detroit,USA"}]},{"given":"Hui","family":"Zhu","sequence":"additional","affiliation":[{"name":"Wayne State University,Computer Science Department,Detroit,USA"}]},{"given":"Prashant","family":"Khanduri","sequence":"additional","affiliation":[{"name":"Wayne State University,Computer Science Department,Detroit,USA"}]},{"given":"Dongxiao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Wayne State University,Computer Science Department,Detroit,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref2"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3447685"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref6","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"ICML","author":"Touvron"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3491231"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref10","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"NeurIPS"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01332"},{"article-title":"Focalunetr: A focal transformer for boundary-aware segmentation of ct images","volume-title":"MICCAI","author":"Li","key":"ref15"},{"article-title":"Auto-prompting sam for mobile friendly 3d medical image segmentation","volume-title":"WACV","author":"Li","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1379"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.320"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/103"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref24","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"NeurIPS"},{"key":"ref25","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"ICML","author":"Shrikumar"},{"key":"ref26","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"ICML","author":"Sundararajan"},{"article-title":"Rise: Randomized input sampling for explanation of black-box models","year":"2018","author":"Petsiuk","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/396"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/50"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17533"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"article-title":"Attcat: Explaining transformers via attentive class activation tokens","volume-title":"NeurIPS","author":"Qiang","key":"ref34"},{"article-title":"On the robustness of interpretability methods","year":"2018","author":"Alvarez-Melis","key":"ref35"},{"key":"ref36","article-title":"Sanity checks for saliency maps","volume-title":"NeurIPS","volume":"31","author":"Adebayo"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_14"},{"article-title":"Distilling a neural network into a soft decision tree","year":"2017","author":"Frosst","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11501"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/371"},{"article-title":"Saliency learning: Teaching the model where to pay attention","year":"2019","author":"Ghaeini","key":"ref41"},{"key":"ref42","article-title":"Improving deep learning interpretability by saliency guided training","author":"Ismail","year":"2021","journal-title":"NeurIPS"},{"article-title":"Attention-based interpretability with concept transformers","volume-title":"ICLR","author":"Rigotti","key":"ref43"},{"key":"ref44","first-page":"11 162","article-title":"Vit-net: Interpretable vision transformers with neural tree decoder","volume-title":"ICML","author":"Kim"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00304"},{"key":"ref46","first-page":"24 273","article-title":"A framework to learn with interpretation","volume":"34","author":"Parekh","year":"2021","journal-title":"NeurIPS"},{"article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","year":"2013","author":"Simonyan","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"article-title":"Openxai: Towards a transparent evaluation of model explanations","year":"2022","author":"Agarwal","key":"ref50"},{"key":"ref51","first-page":"194","article-title":"Contextual explanation networks","volume":"21","author":"Al-Shedivat","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01008"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00265-z"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.07.010"},{"key":"ref56","article-title":"This looks like that: deep learning for interpretable image recognition","volume":"32","author":"Chen","year":"2019","journal-title":"NeurIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/373"},{"article-title":"Deepvit: Towards deeper vision transformer","year":"2021","author":"Zhou","key":"ref58"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1282"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19918"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00455"},{"key":"ref65","article-title":"Explaining information flow inside vision transformers using markov chain","author":"Yuan","year":"2021","journal-title":"eXplainable AI approaches for debugging and diagnosis"},{"key":"ref66","first-page":"24 898","article-title":"Ia-red: Interpretability-aware redundancy reduction for vision transformers","volume":"34","author":"Pan","year":"2021","journal-title":"NeurIPS"},{"issue":"7","key":"ref67","article-title":"Distilling the knowledge in a neural network","volume":"2","author":"Hinton","year":"2015"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/bigdata52589.2021.9671988"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0069"},{"issue":"1","key":"ref70","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"The Journal of Machine Learning Research"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26044"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482126"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28077"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00022"},{"key":"ref75","first-page":"2046","article-title":"Do input gradients highlight discriminative features?","volume":"34","author":"Shah","year":"2021","journal-title":"NeurIPS"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227842.pdf?arnumber=11227842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:25:39Z","timestamp":1763191539000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227842","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}