{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T03:52:35Z","timestamp":1770695555554,"version":"3.49.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1007\/s13042-025-02911-7","type":"journal-article","created":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T09:02:26Z","timestamp":1768640546000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Am-sam: a spatially-aware prompt learning and mask calibration framework for few-shot semantic segmentation"],"prefix":"10.1007","volume":"17","author":[{"given":"Yuchen","family":"Li","sequence":"first","affiliation":[]},{"given":"Li","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Youwei","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Pengtao","family":"Xie","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,17]]},"reference":[{"key":"2911_CR1","doi-asserted-by":"crossref","unstructured":"Xu H, Gao Y, Yu F, Darrell T (2017) End-to-end learning of driving models from large-scale video dataset, pp 2174\u20132182","DOI":"10.1109\/CVPR.2017.376"},{"key":"2911_CR2","doi-asserted-by":"crossref","unstructured":"Cheng B, Collins MD, Zhu Y, Liu T, Huang TS, Adam H, Chen, L.-C.: Panoptic-deeplab, (2020) A simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12475\u201312485","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"2911_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3314512","author":"G Rossolini","year":"2023","unstructured":"Rossolini G, Nesti F, D\u2019Amico G, Nair S, Biondi A, Buttazzo G (2023) On the real-world adversarial robustness of real-time semantic segmentation models for autonomous driving. IEEE Trans Neural Netw Learn Syst. https:\/\/doi.org\/10.1109\/TNNLS.2023.3314512","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2911_CR4","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pp 234\u2013241 . Springer","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2911_CR5","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, Lu L, Yuille AL, Zhou Y (2021) Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306"},{"key":"2911_CR6","doi-asserted-by":"crossref","unstructured":"Tzelepi M, Tefas A (2021) Semantic scene segmentation for robotics applications. In: 2021 12th international conference on information, intelligence, systems & applications (IISA), pp 1\u20134 . IEEE","DOI":"10.1109\/IISA52424.2021.9555526"},{"key":"2911_CR7","doi-asserted-by":"crossref","unstructured":"Zhang H, Han B, Ip CY, Mohapatra P (2020) Slimmer: accelerating 3d semantic segmentation for mobile augmented reality. IEEE, pp 603\u2013612","DOI":"10.1109\/MASS50613.2020.00079"},{"issue":"11","key":"2911_CR8","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"2911_CR9","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"4","key":"2911_CR10","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2911_CR11","unstructured":"Bommasani R, Hudson DA, Adeli E, Altman R, Arora S, Arx S, Bernstein MS, Bohg J, Bosselut A, Brunskill E, et al (2021) On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258"},{"key":"2911_CR12","doi-asserted-by":"crossref","unstructured":"Zhou C, Li Q, Li C, Yu J, Liu Y, Wang G, Zhang K, Ji C, Yan Q, He L, et al (2024) A comprehensive survey on pretrained foundation models: a history from bert to chatgpt. Int J Mach Learn Cybern, pp 1\u201365","DOI":"10.1007\/s13042-024-02443-6"},{"key":"2911_CR13","doi-asserted-by":"crossref","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, Xiao T, Whitehead S, Berg AC, Lo W-Y (2023) Segment anything. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4015\u20134026","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2911_CR14","doi-asserted-by":"crossref","unstructured":"Zhang K, Liu D (2023) Customized segment anything model for medical image segmentation. arXiv preprint arXiv:2304.13785","DOI":"10.2139\/ssrn.4495221"},{"key":"2911_CR15","unstructured":"Zhang L, Liang Y, Zhang R, Javadi A, Xie P (2024) Blo-sam: bi-level optimization based finetuning of the segment anything model for overfitting-preventing semantic segmentation In: Forty-first international conference on machine learning"},{"issue":"7","key":"2911_CR16","doi-asserted-by":"publisher","first-page":"2643","DOI":"10.1007\/s13042-023-02054-7","volume":"15","author":"L Qi","year":"2024","unstructured":"Qi L, Li C, Mei T (2024) Crackunet: a novel network with joint network-in-network structure and deformable convolution for pavement crack detection. Int J Mach Learn Cybern 15(7):2643\u20132654","journal-title":"Int J Mach Learn Cybern"},{"issue":"11","key":"2911_CR17","doi-asserted-by":"publisher","first-page":"8687","DOI":"10.1007\/s13042-025-02703-z","volume":"16","author":"Q Gu","year":"2025","unstructured":"Gu Q, Cai R, Zhang H, Pan J, Fan T (2025) Deep-hybridunet: an accurate polyp segmentation method for colonoscopy images based on deep hybrid attention network. Int J Mach Learn Cybern 16(11):8687\u20138704","journal-title":"Int J Mach Learn Cybern"},{"issue":"10","key":"2911_CR18","doi-asserted-by":"publisher","first-page":"3671","DOI":"10.1007\/s13042-023-01857-y","volume":"14","author":"L Li","year":"2023","unstructured":"Li L, Qin J, Lv L, Cheng M, Wang B, Xia D, Wang S (2023) Icunet++: an inception-cbam network based on unet++ for mr spine image segmentation. Int J Mach Learn Cybern 14(10):3671\u20133683","journal-title":"Int J Mach Learn Cybern"},{"key":"2911_CR19","doi-asserted-by":"crossref","unstructured":"Wang D, Shang K, Liang D, Zhu Y (2024) Hybrid-ctunet: a double complementation approach for 3d medical image segmentation. Int J Mach Learn Cybern, pp 1\u201316","DOI":"10.1007\/s13042-024-02469-w"},{"issue":"9","key":"2911_CR20","doi-asserted-by":"publisher","first-page":"6717","DOI":"10.1007\/s13042-025-02642-9","volume":"16","author":"Y Liu","year":"2025","unstructured":"Liu Y, Liu F, Xiao J, Zhang X, Zhang F (2025) Dtla-net: a direct2d transformer with linear angle attention network for multi-organ medical image segmentation. Int J Mach Learn Cybern 16(9):6717\u20136735","journal-title":"Int J Mach Learn Cybern"},{"issue":"6","key":"2911_CR21","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1109\/TMI.2019.2959609","volume":"39","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J (2019) Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging 39(6):1856\u20131867","journal-title":"IEEE Trans Med Imaging"},{"key":"2911_CR22","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929"},{"key":"2911_CR23","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2911_CR24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3461779","author":"H Bi","year":"2024","unstructured":"Bi H, Feng Y, Diao W, Wang P, Mao Y, Fu K, Wang H, Sun X (2024) Prompt-and-transfer: dynamic class-aware enhancement for few-shot segmentation. IEEE Trans Pattern Anal Mach Intell. https:\/\/doi.org\/10.1109\/TPAMI.2024.3461779","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"7","key":"2911_CR25","doi-asserted-by":"publisher","first-page":"5560","DOI":"10.1109\/TCSVT.2024.3358679","volume":"34","author":"Z Chang","year":"2024","unstructured":"Chang Z, Gao X, Li N, Zhou H, Lu Y (2024) Drnet: disentanglement and recombination network for few-shot semantic segmentation. IEEE Trans Circuits Syst Video Technol 34(7):5560\u20135574","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"2911_CR26","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J (2021). Learning transferable visual models from natural language supervision. In: International conference on machine learning, PMLR, pp 8748\u20138763"},{"key":"2911_CR27","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, Li Y, Doll\u00e1r P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp 16000\u201316009","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2911_CR28","unstructured":"Zhao X, Ding W, An Y, Du Y, Yu T, Li M, Tang M, Wang J (2023) Fast segment anything. arXiv preprint arXiv:2306.12156"},{"key":"2911_CR29","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"issue":"10","key":"2911_CR30","doi-asserted-by":"publisher","first-page":"4589","DOI":"10.1007\/s13042-024-02175-7","volume":"15","author":"Y Wen","year":"2024","unstructured":"Wen Y, Wang L (2024) Yolo-sd: Simulated feature fusion for few-shot industrial defect detection based on yolov8 and stable diffusion. Int J Mach Learn Cybern 15(10):4589\u20134601","journal-title":"Int J Mach Learn Cybern"},{"key":"2911_CR31","unstructured":"Jocher G, Chaurasia A, Qiu J Ultralytics YOLOv8. https:\/\/github.com\/ultralytics\/ultralytics"},{"issue":"2","key":"2911_CR32","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W (2022) Lora: Low-rank adaptation of large language models. ICLR 1(2):3","journal-title":"ICLR"},{"key":"2911_CR33","doi-asserted-by":"crossref","unstructured":"Tejero JG, Schmid M, Neila PM, Zinkernagel MS, Wolf S, Sznitman R (2025) Sam-da: Decoder adapter for efficient medical domain adaptation. In: 2025 IEEE\/CVF winter conference on applications of computer vision (WACV) IEEE, pp 6775\u20136784","DOI":"10.1109\/WACV61041.2025.00659"},{"key":"2911_CR34","unstructured":"Shaharabany T, Dahan A, Giryes R, Wolf L (2023) Autosam: Adapting sam to medical images by overloading the prompt encoder. arXiv preprint arXiv:2306.06370"},{"key":"2911_CR35","unstructured":"Zhang Y, Cheng T, Hu R, Liu H, Ran L, Chen X, Liu W, Wang X, et al (2024) Evf-sam: Early vision-language fusion for text-prompted segment anything model. arXiv preprint arXiv:2406.20076"},{"key":"2911_CR36","unstructured":"Sakurai K, Shimizu R, Goto M (2025)Vision and language reference prompt into sam for few-shot segmentation. arXiv preprint arXiv:2502.00719"},{"key":"2911_CR37","unstructured":"Ravi N, Gabeur V, Hu YT, Hu R, Ryali C, Ma T, Khedr H, R\u00e4dle R, Rolland C, Gustafson L, et al (2024) Sam 2: Segment anything in images and videos. arXiv preprint arXiv:2408.00714"},{"key":"2911_CR38","unstructured":"Xu Q, Zhu L, Liu X, Lin G, Long C, Li Z, Zhao R (2025) Unlocking the power of sam 2 for few-shot segmentation"},{"issue":"2","key":"2911_CR39","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1007\/s13042-024-02318-w","volume":"16","author":"Y Zheng","year":"2025","unstructured":"Zheng Y, Gan W, Chen Z, Qi Z, Liang Q, Yu PS (2025) Large language models for medicine: a survey. Int J Mach Learn Cybern 16(2):1015\u20131040","journal-title":"Int J Mach Learn Cybern"},{"key":"2911_CR40","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: Single shot multibox detector. In: Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp 21\u201337 . Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2911_CR41","doi-asserted-by":"publisher","unstructured":"Jocher G Ultralytics YOLOv5. https:\/\/doi.org\/10.5281\/zenodo.3908559. https:\/\/github.com\/ultralytics\/yolov5","DOI":"10.5281\/zenodo.3908559"},{"key":"2911_CR42","unstructured":"Anwar T, Kucev R, Kerneler K (2021) Segmentation Full Body TikTok Dancing Dataset. https:\/\/www.kaggle.com\/datasets\/tapakah68\/segmentation-full-body-tiktok-dancing-dataset. Accessed 28 May 2024"},{"key":"2911_CR43","unstructured":"Shenoy V (2024) Human Segmentation Dataset. https:\/\/github.com\/VikramShenoy97\/Human-Segmentation-Dataset. Accessed 02 July 2024"},{"key":"2911_CR44","doi-asserted-by":"crossref","unstructured":"Codella NC, Gutman D, Celebi ME, Helba B, Marchetti MA, Dusza SW, Kalloo A, Liopyris K, Mishra N, Kittler H (2018) Skin lesion analysis toward melanoma detection: a challenge at the 2017 international symposium on biomedical imaging (isbi), hosted by the international skin imaging collaboration (isic). In: 2018 IEEE 15th International symposium on biomedical imaging (ISBI 2018), pp 168\u2013172 . IEEE","DOI":"10.1109\/ISBI.2018.8363547"},{"issue":"1","key":"2911_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl P, Rosendahl C, Kittler H (2018) The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Scientific data 5(1):1\u20139","journal-title":"Scientific data"},{"key":"2911_CR46","doi-asserted-by":"crossref","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, Wang M (2022). Swin-unet: Unet-like pure transformer for medical image segmentation. In: European conference on computer vision, Springer, pp 205\u2013218","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"2911_CR47","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106173","volume":"150","author":"W Zhang","year":"2022","unstructured":"Zhang W, Fu C, Zheng Y, Zhang F, Zhao Y, Sham C-W (2022) Hsnet: a hybrid semantic network for polyp segmentation. Comput Biol Med 150:106173","journal-title":"Comput Biol Med"},{"key":"2911_CR48","doi-asserted-by":"crossref","unstructured":"Fan Q, Pei W, Tai Y-W, Tang C-K (2022). Self-support few-shot semantic segmentation. In: European conference on computer vision Springer, pp 701\u2013719","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"2911_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103547","volume":"102","author":"J Wu","year":"2025","unstructured":"Wu J, Wang Z, Hong M, Ji W, Fu H, Xu Y, Xu M, Jin Y (2025) Medical sam adapter: adapting segment anything model for medical image segmentation. Med Image Anal 102:103547","journal-title":"Med Image Anal"},{"key":"2911_CR50","unstructured":"Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02911-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02911-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02911-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T09:40:35Z","timestamp":1770630035000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02911-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["2911"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02911-7","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"3 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"35"}}