{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T20:05:09Z","timestamp":1780949109802,"version":"3.54.1"},"reference-count":107,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476029"],"award-info":[{"award-number":["62476029"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225601"],"award-info":[{"award-number":["62225601"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2052"],"award-info":[{"award-number":["U23B2052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds for the Beijing University of Posts","award":["2025TSQY08"],"award-info":[{"award-number":["2025TSQY08"]}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L242025"],"award-info":[{"award-number":["L242025"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX20242081"],"award-info":[{"award-number":["CX20242081"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1109\/tpami.2026.3674640","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:15:27Z","timestamp":1773692127000},"page":"8661-8677","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8769-9533","authenticated-orcid":false,"given":"Zijin","family":"Yin","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Visual Computing Center, King Abdullah University of Science and Technology, Jeddah, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4726-093X","authenticated-orcid":false,"given":"Kongming","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"China Telecom Artificial Intelligence Technology Company Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongjiang","family":"He","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-2488","authenticated-orcid":false,"given":"Zhanyu","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9045-1339","authenticated-orcid":false,"given":"Jun","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02068"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00325"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_35"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1094"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02055"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01951"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref15","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02124"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1072-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.148"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_25"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00831-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3063289"},{"key":"ref27","first-page":"2376","article-title":"Counterfactual visual explanations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Goyal"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_23"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00109"},{"key":"ref30","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2018"},{"key":"ref31","article-title":"Discovering bugs in vision models using off-the-shelf image generation and captioning","author":"Wiles","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0027"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00996"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01119"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01446"},{"key":"ref36","article-title":"Dataset interfaces: Diagnosing model failures using controllable counterfactual generation","author":"Vendrow","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00469"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01138"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref40","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01332"},{"key":"ref42","article-title":"Benchmarking the robustness of optical flow estimation to corruptions","author":"Yi","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref44","article-title":"Inversion-free image editing with natural language","author":"Xu","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00674"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01647"},{"key":"ref48","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref49","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2836461"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612274"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00910"},{"key":"ref54","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref56","article-title":"LLAMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref57","article-title":"The LLAMA 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591513"},{"key":"ref59","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00099"},{"key":"ref61","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref64","first-page":"9453","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Barbu"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530164"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0819"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612145"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref74","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3047209"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref78","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref79","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00394"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref87","article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref88","article-title":"Detectron2","author":"Wu","year":"2019"},{"key":"ref89","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref91","article-title":"Augmix: A simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2019"},{"key":"ref92","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00693"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref95","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2105.07581"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref98","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dehghani"},{"key":"ref99","article-title":"Intra-& extra-source exemplar-based style synthesis for improved domain generalization","author":"Li","year":"2023"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01462"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01048"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref105","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref107","first-page":"677","article-title":"On the importance of gradients for detecting distributional shifts in the wild","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11552636\/11435638.pdf?arnumber=11435638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T19:51:39Z","timestamp":1780948299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11435638\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":107,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3674640","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}