{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:48:15Z","timestamp":1791686895191,"version":"4.3.4"},"reference-count":79,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.neunet.2026.109689","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:22:42Z","timestamp":1791566562000},"page":"109689","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Test-time optimization for domain adaptive open vocabulary segmentation"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6544-8059","authenticated-orcid":false,"given":"Ulindu","family":"De Silva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7712-6056","authenticated-orcid":false,"given":"Didula","family":"Samaraweera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3244-4146","authenticated-orcid":false,"given":"Sasini","family":"Wanigathunga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5822-667X","authenticated-orcid":false,"given":"Kavindu","family":"Kariyawasam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2374-7804","authenticated-orcid":false,"given":"Kanchana","family":"Ranasinghe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-7161","authenticated-orcid":false,"given":"Muzammal","family":"Naseer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1034-7513","authenticated-orcid":false,"given":"Ranga","family":"Rodrigo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109689_bib0001","doi-asserted-by":"crossref","first-page":"80396","DOI":"10.52202\/075280-3525","article-title":"Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization","volume":"36","author":"Abdul Samadh","year":"2023","journal-title":"Advanced Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109689_bib0002","unstructured":"AI@Meta (2024). Llama 3 model card, https:\/\/github.com\/metallama\/llama3\/blob\/main\/MODEL_CARD.md."},{"key":"10.1016\/j.neunet.2026.109689_bib0003","unstructured":"Alemohammad, H., & Booth, K. (2020). LandCoverNet: A global benchmark land cover classification training dataset. arXiv preprint arXiv: 2012.03111."},{"key":"10.1016\/j.neunet.2026.109689_bib0004","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"21147","article-title":"Zerowaste dataset: Towards deformable object segmentation in cluttered scenes","author":"Bashkirova","year":"2022"},{"key":"10.1016\/j.neunet.2026.109689_bib0005","unstructured":"Bianchi, E., & Hebdon, M. (2021). Corrosion condition state semantic segmentation dataset [Data set]. University Libraries, Virginia Tech. 10.7294\/16624663."},{"key":"10.1016\/j.neunet.2026.109689_bib0006","article-title":"What a MESS: Multi-domain evaluation of zero-shot semantic segmentation","author":"Blumenstiel","year":"2023","journal-title":"ArXiv"},{"key":"10.1016\/j.neunet.2026.109689_bib0007","doi-asserted-by":"crossref","first-page":"4623","DOI":"10.1007\/s11263-025-02401-x","article-title":"Multi-source domain adaptation by causal-guided adaptive multimodal diffusion networks","volume":"133","author":"Cai","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109689_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.103859","article-title":"Make source-free transfer great: Dynamic uncertainty-driven confident fusion for multi-source-free domain adaptation","volume":"127","author":"Cai","year":"2026","journal-title":"Information Fusion"},{"key":"10.1016\/j.neunet.2026.109689_bib0009","unstructured":"Chen, R., Rong, Y., Guo, S., Han, J., Sun, F., Xu, T., & Huang, W. (2022). Smoothing matters: Momentum transformer for domain adaptive semantic segmentation. 10.48550\/arXiv.2203.07988."},{"key":"10.1016\/j.neunet.2026.109689_bib0010","doi-asserted-by":"crossref","unstructured":"Chiquier, M., Mall, U., & Vondrick, C. (2024). Evolving interpretable visual classifiers with large language models. arXiv preprint arXiv: 2404.09941.","DOI":"10.1007\/978-3-031-73039-9_11"},{"key":"10.1016\/j.neunet.2026.109689_bib0011","series-title":"IEEE conf. comput. vis. pattern recog.","article-title":"CAT-seg: Cost aggregation for open-vocabulary semantic segmentation","author":"Cho","year":"2024"},{"key":"10.1016\/j.neunet.2026.109689_bib0012","series-title":"Computer graphics forum","first-page":"261","article-title":"Semantic segmentation in art paintings","volume":"vol. 41","author":"Cohen","year":"2022"},{"key":"10.1016\/j.neunet.2026.109689_bib0013","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"11583","article-title":"Decoupling zero-shot semantic segmentation","author":"Ding","year":"2022"},{"key":"10.1016\/j.neunet.2026.109689_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.envsoft.2022.105333","article-title":"Atlantis: A benchmark for semantic segmentation of waterbody images","volume":"149","author":"Erfani","year":"2022","journal-title":"Environmental Modelling & Software"},{"issue":"387","key":"10.1016\/j.neunet.2026.109689_bib0015","article-title":"Source-free domain adaptation via multi-view contrastive learning","volume":"82","author":"Farhadi","year":"2026","journal-title":"The Journal of Supercomputing"},{"issue":"9","key":"10.1016\/j.neunet.2026.109689_bib0016","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1109\/TBME.2012.2205687","article-title":"An ensemble classification-based approach applied to retinal blood vessel segmentation","volume":"59","author":"Fraz","year":"2012","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"10.1016\/j.neunet.2026.109689_bib0017","unstructured":"Gemma Team, T. M., Hardin, C., Dadashi, R., Bhupatiraju, S., Sifre, L., Rivi\u00e8re, M., Kale, M. S., Love, J., Tafti, P., & Hussenot, L., et al. (2024). Gemma, 10.34740\/KAGGLE\/M\/3301."},{"key":"10.1016\/j.neunet.2026.109689_bib0018","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume":"17","author":"Grandvalet","year":"2004","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109689_bib0019","series-title":"Computer vision-ECCV 2014 workshops: Zurich, switzerland, september 6-7 and 12, 2014, proceedings, part IV 13","first-page":"105","article-title":"A crop\/weed field image dataset for the evaluation of computer vision based precision agriculture tasks","author":"Haug","year":"2015"},{"key":"10.1016\/j.neunet.2026.109689_bib0020","doi-asserted-by":"crossref","unstructured":"He, Q., Peng, J., Jiang, Z., Hu, X., Zhang, J., Nie, Q., Wang, Y., & Wang, C. (2024). PointSeg: A training-free paradigm for 3D scene segmentation via foundation models. arXiv preprint arXiv: 2403.06403.","DOI":"10.1109\/ICCVW69036.2025.00279"},{"key":"10.1016\/j.neunet.2026.109689_bib0021","series-title":"IEEE conf. comput. vis. pattern recog.","article-title":"Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation","author":"Hoyer","year":"2022"},{"key":"10.1016\/j.neunet.2026.109689_bib0022","series-title":"Eur. conf. comput. vis.","article-title":"HRDA: Context-aware high-resolution domain-adaptive semantic segmentation","author":"Hoyer","year":"2022"},{"key":"10.1016\/j.neunet.2026.109689_bib0023","series-title":"IEEE conf. comput. vis. pattern recog.","article-title":"MIC: Masked image consistency for context-enhanced domain adaptation","author":"Hoyer","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0024","series-title":"2020 IEEE\/RSJ International conference on intelligent robots and systems (IROS)","first-page":"1769","article-title":"Semantic segmentation of underwater imagery: Dataset and benchmark","author":"Islam","year":"2020"},{"key":"10.1016\/j.neunet.2026.109689_bib0025","series-title":"Multimedia modeling: 27th international conference, MMM 2021, prague, czech republic, june 22\u201324, 2021, proceedings, part II 27","first-page":"218","article-title":"Kvasir-instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy","author":"Jha","year":"2021"},{"key":"10.1016\/j.neunet.2026.109689_bib0026","series-title":"ICML","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","author":"Jia","year":"2021"},{"key":"10.1016\/j.neunet.2026.109689_bib0027","doi-asserted-by":"crossref","unstructured":"Jia, M., Tang, L., Chen, B.-C., Cardie, C., Belongie, S. J., Hariharan, B., & Lim, S. N. (2022). Visual prompt tuning. ArXiv, abs\/2203.12119. https:\/\/api.semanticscholar.org\/CorpusID:247618727.","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"10.1016\/j.neunet.2026.109689_bib0028","unstructured":"Jiang, A. Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D. S., de las, C. D., Bressand, F., Lengyel, G., Lample, G., Saulnier, L. et al. (2023). Mistral 7B. arXiv preprint arXiv: 2310.06825."},{"key":"10.1016\/j.neunet.2026.109689_bib0029","unstructured":"Jin, S., Jiang, X., Huang, J., Lu, L., & Lu, S. (2024). LLMs meet VLMs: Boost open vocabulary object detection with fine-grained descriptors. arXiv preprint arXiv: 2402.04630."},{"key":"10.1016\/j.neunet.2026.109689_bib0030","series-title":"Int. conf. comput. vis.","article-title":"Generalize then adapt: Source-free domain adaptive semantic segmentation","author":"Kundu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109689_bib0031","series-title":"Eur. conf. comput. vis.","article-title":"ProxyCLIP: Proxy attention improves CLIP for open-vocabulary segmentation","author":"Lan","year":"2024"},{"key":"10.1016\/j.neunet.2026.109689_bib0032","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5982","article-title":"Exploring efficient open-vocabulary segmentation in the remote sensing","volume":"vol. 40","author":"Li","year":"2026"},{"key":"10.1016\/j.neunet.2026.109689_bib0033","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","article-title":"Images as noisy labels: Unleashing the potential of the diffusion model for open-vocabulary semantic segmentation","author":"Li","year":"2025"},{"key":"10.1016\/j.neunet.2026.109689_bib0034","series-title":"Eur. conf. comput. vis.","article-title":"Content-consistent matching for domain adaptive semantic segmentation","author":"Li","year":"2020"},{"key":"10.1016\/j.neunet.2026.109689_bib0035","series-title":"Int. conf. learn. represent.","article-title":"Masked unsupervised self-training for label-free image classification","author":"Li","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0036","unstructured":"Li, J., Zhao, J., Wei, Y., Lang, C., Li, Y., Sim, T., Yan, S., & Feng, J. (2017). Multiple-human parsing in the wild. arXiv preprint arXiv: 1705.07206."},{"key":"10.1016\/j.neunet.2026.109689_bib0037","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"7061","article-title":"Open-vocabulary semantic segmentation with mask-adapted clip","author":"Liang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0038","series-title":"International conference on machine learning","first-page":"6028","article-title":"Do we really need to access the source data? Source hypothesis transfer for unsupervised domain adaptation","author":"Liang","year":"2020"},{"key":"10.1016\/j.neunet.2026.109689_bib0039","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"5245","article-title":"InvSeg: Test-time prompt inversion for semantic segmentation","author":"Lin","year":"2025"},{"key":"10.1016\/j.neunet.2026.109689_bib0040","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.neucom.2019.01.036","article-title":"DeepCrack: A deep hierarchical feature learning architecture for crack segmentation","volume":"338","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.109689_bib0041","series-title":"ACM MM","article-title":"Bidirectional self-training with multiple anisotropic prototypes for domain adaptive semantic segmentation","author":"Lu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109689_bib0042","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.isprsjprs.2020.05.009","article-title":"UAVid: A semantic segmentation dataset for uav imagery","volume":"165","author":"Lyu","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"10.1016\/j.neunet.2026.109689_bib0043","doi-asserted-by":"crossref","first-page":"65252","DOI":"10.52202\/075280-2847","article-title":"SwapPrompt: Test-time prompt adaptation for vision-language models","volume":"36","author":"Ma","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109689_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2021.104349","article-title":"CryoNuSeg: A dataset for nuclei instance segmentation of cryosectioned h&e-stained histological images","volume":"132","author":"Mahbod","year":"2021","journal-title":"Computers in Biology and Medicine"},{"key":"10.1016\/j.neunet.2026.109689_bib0045","series-title":"Eur. conf. comput. vis.","article-title":"CoPT: Unsupervised domain adaptive segmentation using domain-agnostic text embeddings","author":"Mata","year":"2024"},{"issue":"1","key":"10.1016\/j.neunet.2026.109689_bib0046","doi-asserted-by":"crossref","first-page":"7249","DOI":"10.1038\/s41598-021-86650-z","article-title":"Towards global flood mapping onboard low cost satellites with machine learning","volume":"11","author":"Mateo-Garcia","year":"2021","journal-title":"Scientific Reports"},{"key":"10.1016\/j.neunet.2026.109689_bib0047","series-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR 2023)","article-title":"Visual classification via description from large language models","author":"Menon","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0048","series-title":"The thirty-ninth annual conference on neural information processing systems","article-title":"Test-time adaptation of vision-language models for open-vocabulary semantic segmentation","author":"Noori","year":"2025"},{"key":"10.1016\/j.neunet.2026.109689_bib0049","doi-asserted-by":"crossref","unstructured":"Ozturk, E., Prabhushankar, M., & AlRegib, G. (2024). Intelligent multi-view test time augmentation. arXiv preprint arXiv: 2406.08593.","DOI":"10.1109\/ICIP51287.2024.10647871"},{"key":"10.1016\/j.neunet.2026.109689_bib0050","series-title":"ICML","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2026.109689_bib0051","doi-asserted-by":"crossref","first-page":"89644","DOI":"10.1109\/ACCESS.2021.3090981","article-title":"FloodNet: A high resolution aerial imagery dataset for post flood scene understanding","volume":"9","author":"Rahnemoonfar","year":"2021","journal-title":"IEEE Access : Practical Innovations, Open Solutions"},{"key":"10.1016\/j.neunet.2026.109689_bib0052","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"5571","article-title":"Perceptual grouping in contrastive vision-language models","author":"Ranasinghe","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0053","unstructured":"Ren, T., Liu, S., Zeng, A., Lin, J., Li, K., Cao, H., Chen, J., Huang, X., Chen, Y., Yan, F., Zeng, Z., Zhang, H., Li, F., Yang, J., Li, H., Jiang, Q., & Zhang, L. (2024). Grounded SAM: Assembling open-world models for diverse visual tasks. 10.48550\/arXiv.2401.14159."},{"key":"10.1016\/j.neunet.2026.109689_bib0054","series-title":"Int. conf. comput. vis.","first-page":"7374","article-title":"Guided curriculum model adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation","author":"Sakaridis","year":"2019"},{"key":"10.1016\/j.neunet.2026.109689_bib0055","unstructured":"Seibold, C., Rei\u00df, S., Sarfraz, S., Fink, M. A., Mayer, V., Sellner, J., Kim, M. S., Maier-Hein, K. H., Kleesiek, J., & Stiefelhagen, R. (2022). Detailed annotations of chest X-rays via CT projection for report understanding. arXiv preprint arXiv: 2210.03416."},{"key":"10.1016\/j.neunet.2026.109689_bib0056","series-title":"Adv. neural inform. process. syst.","article-title":"Active vision reinforcement learning under limited visual observability","author":"Shang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0057","series-title":"2020 IEEE International conference on robotics and automation (ICRA)","first-page":"9441","article-title":"PST900: RGB-thermal calibration, dataset and segmentation network","author":"Shivakumar","year":"2020"},{"key":"10.1016\/j.neunet.2026.109689_bib0058","doi-asserted-by":"crossref","first-page":"14274","DOI":"10.52202\/068431-1038","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume":"35","author":"Shu","year":"2022","journal-title":"Advanced Neural Information Processing Systemszhou2022coop"},{"key":"10.1016\/j.neunet.2026.109689_bib0059","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"2517","article-title":"Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation","author":"Vu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109689_bib0060","series-title":"Technical Report","article-title":"Caltech-UCSD birds 200","author":"Wah","year":"2011"},{"key":"10.1016\/j.neunet.2026.109689_bib0061","unstructured":"Wang, Z., Liu, X., Suganuma, M., & Okatani, T. (2022). Cross-region domain adaptation for class-level alignment. arXiv preprint arXiv: 2109.06422."},{"key":"10.1016\/j.neunet.2026.109689_bib0062","series-title":"IEEE conf. comput. vis. pattern recog. worksh.","first-page":"28","article-title":"isaid: A large-scale dataset for instance segmentation in aerial images","author":"Waqas Zamir","year":"2019"},{"key":"10.1016\/j.neunet.2026.109689_bib0063","series-title":"Proceedings of the 29th ACM international conference on multimedia","first-page":"506","article-title":"A large-scale benchmark for food image segmentation","author":"Wu","year":"2021"},{"key":"10.1016\/j.neunet.2026.109689_bib0064","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"320","article-title":"CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation","author":"Wysocza\u0144ska","year":"2024"},{"key":"10.1016\/j.neunet.2026.109689_bib0065","doi-asserted-by":"crossref","first-page":"30812","DOI":"10.1109\/ACCESS.2026.3667444","article-title":"CGSeg: Cross-aggregation and gated fusion for open-vocabulary semantic segmentation","volume":"14","author":"Xia","year":"2026","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.109689_bib0066","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"2945","article-title":"Side adapter network for open-vocabulary semantic segmentation","author":"Xu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0067","series-title":"Eur. conf. comput. vis.","first-page":"736","article-title":"A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model","author":"Xu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109689_bib0068","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","first-page":"10699","article-title":"Test-time multi-prompt adaptation for open-vocabulary remote sensing image segmentation","author":"Yang","year":"2026"},{"key":"10.1016\/j.neunet.2026.109689_bib0069","unstructured":"Yilmaz, G., Peng, S., Pollefeys, M., Engelmann, F., & Blum, H. (2024). OpenDAS: Open-vocabulary domain adaptation for 2D and 3D segmentation. arXiv preprint arXiv: 2405.20141."},{"key":"10.1016\/j.neunet.2026.109689_bib0070","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"2636","article-title":"BDD100K: A diverse driving dataset for heterogeneous multitask learning","author":"Yu","year":"2020"},{"key":"10.1016\/j.neunet.2026.109689_bib0071","series-title":"Int. conf. learn. represent.","article-title":"KoLA: Carefully benchmarking world knowledge of large language models","author":"Yu","year":"2024"},{"key":"10.1016\/j.neunet.2026.109689_bib0072","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume":"33","author":"Yu","year":"2020","journal-title":"Advanced Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109689_bib0073","series-title":"Int. conf. comput. vis.","first-page":"1020","article-title":"A simple framework for open-vocabulary segmentation and detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109689_bib0074","series-title":"IEEE conf. comput. vis. pattern recog.","article-title":"Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation","author":"Zhang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109689_bib0075","series-title":"Int. conf. learn. represent.","article-title":"Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neunet.2026.109689_bib0076","series-title":"IJCAI","article-title":"Unsupervised scene adaptation with memory regularization in vivo","author":"Zheng","year":"2020"},{"key":"10.1016\/j.neunet.2026.109689_bib0077","series-title":"IEEE conf. comput. vis. pattern recog.","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"issue":"9","key":"10.1016\/j.neunet.2026.109689_bib0078","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2026.109689_bib0079","series-title":"IEEE conf. comput. vis. pattern recog.","first-page":"15116","article-title":"Generalized decoding for pixel, image, and language","author":"Zou","year":"2023"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011445?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026011445?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:35:27Z","timestamp":1791686127000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026011445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":79,"alternative-id":["S0893608026011445"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109689","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Test-time optimization for domain adaptive open vocabulary segmentation","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109689","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"109689"}}