{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T06:35:56Z","timestamp":1768804556584,"version":"3.49.0"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0112400"],"award-info":[{"award-number":["2021ZD0112400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1908214"],"award-info":[{"award-number":["U1908214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["D23006"],"award-info":[{"award-number":["D23006"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["DLUXK-2024-QN-017"],"award-info":[{"award-number":["DLUXK-2024-QN-017"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1016\/j.neunet.2025.107527","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T11:27:34Z","timestamp":1746530854000},"page":"107527","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["FDC: Feature Dropout Consistency for unsupervised domain adaptation semantic segmentation"],"prefix":"10.1016","volume":"189","author":[{"given":"Chaoyu","family":"Rao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6299-2795","authenticated-orcid":false,"given":"Wanshu","family":"Fan","sequence":"additional","affiliation":[]},{"given":"Cong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xiaopeng","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Dongsheng","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107527_b1","series-title":"CVPR","first-page":"15384","article-title":"Self-supervised augmentation consistency for adapting semantic segmentation","author":"Araslanov","year":"2021"},{"key":"10.1016\/j.neunet.2025.107527_b2","series-title":"COLT","first-page":"92","article-title":"Combining labeled and unlabeled data with co-training","author":"Blum","year":"1998"},{"key":"10.1016\/j.neunet.2025.107527_b3","series-title":"CVPR","first-page":"1791","article-title":"Crdoco: Pixel-level domain transfer with cross-domain consistency","author":"Chen","year":"2019"},{"issue":"4","key":"10.1016\/j.neunet.2025.107527_b4","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE TPAMI"},{"key":"10.1016\/j.neunet.2025.107527_b5","series-title":"ECCV","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"10.1016\/j.neunet.2025.107527_b6","series-title":"CVPR","first-page":"1290","article-title":"Masked-attention mask transformer for universal image segmentation","author":"Cheng","year":"2022"},{"key":"10.1016\/j.neunet.2025.107527_b7","series-title":"CVPR","first-page":"3213","article-title":"The cityscapes dataset for semantic urban scene understanding","author":"Cordts","year":"2016"},{"key":"10.1016\/j.neunet.2025.107527_b8","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.neunet.2025.107527_b9","first-page":"4749","article-title":"Learning from future: A novel self-training framework for semantic segmentation","volume":"35","author":"Du","year":"2022","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b10","series-title":"Self-ensembling for visual domain adaptation","author":"French","year":"2017"},{"key":"10.1016\/j.neunet.2025.107527_b11","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.ins.2022.11.129","article-title":"CNNs\/ViTs-CNNs\/ViTs: Mutual distillation for unsupervised domain adaptation","volume":"622","author":"Fu","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2025.107527_b12","series-title":"CVPR","first-page":"2427","article-title":"Geometry-consistent generative adversarial networks for one-sided unsupervised domain mapping","author":"Fu","year":"2019"},{"key":"10.1016\/j.neunet.2025.107527_b13","series-title":"CVPR","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neunet.2025.107527_b14","series-title":"ICML","first-page":"1989","article-title":"Cycada: Cycle-consistent adversarial domain adaptation","author":"Hoffman","year":"2018"},{"key":"10.1016\/j.neunet.2025.107527_b15","series-title":"CVPR","first-page":"9924","article-title":"Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation","author":"Hoyer","year":"2022"},{"key":"10.1016\/j.neunet.2025.107527_b16","series-title":"ECCV","first-page":"372","article-title":"HRDA: Context-aware high-resolution domain-adaptive semantic segmentation","author":"Hoyer","year":"2022"},{"key":"10.1016\/j.neunet.2025.107527_b17","series-title":"CVPR","first-page":"11721","article-title":"MIC: Masked image consistency for context-enhanced domain adaptation","author":"Hoyer","year":"2023"},{"key":"10.1016\/j.neunet.2025.107527_b18","series-title":"CVPR","first-page":"15099","article-title":"Simple: Similar pseudo label exploitation for semi-supervised classification","author":"Hu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107527_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108384","article-title":"Multi-level adversarial network for domain adaptive semantic segmentation","volume":"123","author":"Huang","year":"2022","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.107527_b20","series-title":"CVPR","first-page":"7075","article-title":"Domain-agnostic prior for transfer semantic segmentation","author":"Huo","year":"2022"},{"key":"10.1016\/j.neunet.2025.107527_b21","series-title":"WACV","first-page":"1864","article-title":"Mlsl: Multi-level self-supervised learning for domain adaptation with spatially independent and semantically consistent labeling","author":"Iqbal","year":"2020"},{"key":"10.1016\/j.neunet.2025.107527_b22","series-title":"ECCV","first-page":"36","article-title":"Prototypical contrast adaptation for domain adaptive semantic segmentation","author":"Jiang","year":"2022"},{"key":"10.1016\/j.neunet.2025.107527_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107627","article-title":"Structured graph learning for clustering and semi-supervised classification","volume":"110","author":"Kang","year":"2021","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.neunet.2025.107527_b24","first-page":"3569","article-title":"Pixel-level cycle association: A new perspective for domain adaptive semantic segmentation","volume":"33","author":"Kang","year":"2020","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b25","series-title":"CVPR","first-page":"12975","article-title":"Learning texture invariant representation for domain adaptation of semantic segmentation","author":"Kim","year":"2020"},{"key":"10.1016\/j.neunet.2025.107527_b26","series-title":"ECCV","first-page":"440","article-title":"Content-consistent matching for domain adaptive semantic segmentation","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2025.107527_b27","series-title":"CVPR","first-page":"11593","article-title":"Class-balanced pixel-level self-labeling for domain adaptive semantic segmentation","author":"Li","year":"2022"},{"key":"10.1016\/j.neunet.2025.107527_b28","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.ins.2021.01.016","article-title":"Cross adversarial consistency self-prediction learning for unsupervised domain adaptation person re-identification","volume":"559","author":"Li","year":"2021","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2025.107527_b29","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.ins.2023.01.109","article-title":"Pseudo-labeling integrating centers and samples with consistent selection mechanism for unsupervised domain adaptation","volume":"628","author":"Li","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2025.107527_b30","series-title":"CVPR","first-page":"6936","article-title":"Bidirectional learning for domain adaptation of semantic segmentation","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2025.107527_b31","series-title":"ICCV","first-page":"10367","article-title":"Adversarial unsupervised domain adaptation with conditional and label shift: Infer, align and iterate","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107527_b32","series-title":"ICCV","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"8","key":"10.1016\/j.neunet.2025.107527_b33","first-page":"3940","article-title":"Category-level adversarial adaptation for semantic segmentation using purified features","volume":"44","author":"Luo","year":"2021","journal-title":"IEEE TPAMI"},{"key":"10.1016\/j.neunet.2025.107527_b34","series-title":"CVPR","first-page":"2507","article-title":"Taking a closer look at domain shift: Category-level adversaries for semantics consistent domain adaptation","author":"Luo","year":"2019"},{"key":"10.1016\/j.neunet.2025.107527_b35","series-title":"CVPR","first-page":"12435","article-title":"Pixmatch: Unsupervised domain adaptation via pixelwise consistency training","author":"Melas-Kyriazi","year":"2021"},{"key":"10.1016\/j.neunet.2025.107527_b36","series-title":"CVPR","first-page":"4500","article-title":"Image to image translation for domain adaptation","author":"Murez","year":"2018"},{"key":"10.1016\/j.neunet.2025.107527_b37","series-title":"ECCV","first-page":"102","article-title":"Playing for data: Ground truth from computer games","author":"Richter","year":"2016"},{"key":"10.1016\/j.neunet.2025.107527_b38","series-title":"CVPR","first-page":"3234","article-title":"The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes","author":"Ros","year":"2016"},{"key":"10.1016\/j.neunet.2025.107527_b39","series-title":"ICCV","first-page":"10745","article-title":"ACDC: The adverse conditions dataset with correspondences for semantic driving scene understanding","author":"Sakaridis","year":"2021"},{"issue":"6","key":"10.1016\/j.neunet.2025.107527_b40","doi-asserted-by":"crossref","first-page":"3139","DOI":"10.1109\/TPAMI.2020.3045882","article-title":"Map-guided curriculum domain adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation","volume":"44","author":"Sakaridis","year":"2020","journal-title":"IEEE TPAMI"},{"key":"10.1016\/j.neunet.2025.107527_b41","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"Sohn","year":"2020","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b42","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b43","series-title":"WACV","first-page":"1379","article-title":"Dacs: Domain adaptation via cross-domain mixed sampling","author":"Tranheden","year":"2021"},{"key":"10.1016\/j.neunet.2025.107527_b44","series-title":"CVPR","first-page":"7472","article-title":"Learning to adapt structured output space for semantic segmentation","author":"Tsai","year":"2018"},{"key":"10.1016\/j.neunet.2025.107527_b45","series-title":"ICCV","first-page":"1456","article-title":"Domain adaptation for structured output via discriminative patch representations","author":"Tsai","year":"2019"},{"key":"10.1016\/j.neunet.2025.107527_b46","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b47","series-title":"CVPR","first-page":"2517","article-title":"Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation","author":"Vu","year":"2019"},{"key":"10.1016\/j.neunet.2025.107527_b48","series-title":"ECCV","first-page":"642","article-title":"Classes matter: A fine-grained adversarial approach to cross-domain semantic segmentation","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2025.107527_b49","article-title":"Sepico: Semantic-guided pixel contrast for domain adaptive semantic segmentation","author":"Xie","year":"2023","journal-title":"IEEE TPAMI"},{"key":"10.1016\/j.neunet.2025.107527_b50","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b51","series-title":"CVPR","first-page":"4085","article-title":"Fda: Fourier domain adaptation for semantic segmentation","author":"Yang","year":"2020"},{"key":"10.1016\/j.neunet.2025.107527_b52","series-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015"},{"key":"10.1016\/j.neunet.2025.107527_b53","series-title":"ECCV","first-page":"173","article-title":"Object-contextual representations for semantic segmentation","author":"Yuan","year":"2020"},{"key":"10.1016\/j.neunet.2025.107527_b54","first-page":"7281","article-title":"Hrformer: High-resolution vision transformer for dense predict","volume":"34","author":"Yuan","year":"2021","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b55","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.ins.2023.03.078","article-title":"Hypergraph and cross-attention-based unsupervised domain adaptation framework for cross-domain myocardial infarction localization","volume":"633","author":"Yuan","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2025.107527_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.ins.2023.119442","article-title":"MS-IRTNet: Multistage information interaction network for RGB-T semantic segmentation","volume":"647","author":"Zhang","year":"2023","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2025.107527_b57","article-title":"Category anchor-guided unsupervised domain adaptation for semantic segmentation","volume":"32","author":"Zhang","year":"2019","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b58","series-title":"CVPR","first-page":"12414","article-title":"Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2025.107527_b59","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1016\/j.ins.2019.12.005","article-title":"Hybrid adversarial network for unsupervised domain adaptation","volume":"514","author":"Zhang","year":"2020","journal-title":"Information Sciences"},{"key":"10.1016\/j.neunet.2025.107527_b60","article-title":"Multi-source domain adaptation for semantic segmentation","volume":"32","author":"Zhao","year":"2019","journal-title":"NeurIPS"},{"key":"10.1016\/j.neunet.2025.107527_b61","doi-asserted-by":"crossref","unstructured":"Zhao, X., Mithun, N. C., Rajvanshi, A., Chiu, H.-P., & Samarasekera, S. (2024). Unsupervised domain adaptation for semantic segmentation with pseudo label self-refinement. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 2399\u20132409).","DOI":"10.1109\/WACV57701.2024.00239"},{"issue":"2","key":"10.1016\/j.neunet.2025.107527_b62","first-page":"804","article-title":"Context-aware mixup for domain adaptive semantic segmentation","volume":"33","author":"Zhou","year":"2022","journal-title":"IEEE TSCVT"},{"key":"10.1016\/j.neunet.2025.107527_b63","series-title":"ICME","first-page":"01","article-title":"Domain adaptive semantic segmentation via regional contrastive consistency regularization","author":"Zhou","year":"2022"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802500406X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802500406X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T04:05:28Z","timestamp":1762315528000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802500406X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":63,"alternative-id":["S089360802500406X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107527","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"FDC: Feature Dropout Consistency for unsupervised domain adaptation semantic segmentation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107527","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107527"}}