{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:16:51Z","timestamp":1765520211128,"version":"3.48.0"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002512","name":"Kookmin University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002512","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246989","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"9909-9916","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation"],"prefix":"10.1109","author":[{"given":"Seungheon","family":"Song","sequence":"first","affiliation":[{"name":"Kookmin University,College of Computer Science,Seoul,Republic of Korea"}]},{"given":"Jaekoo","family":"Lee","sequence":"additional","affiliation":[{"name":"Kookmin University,College of Computer Science,Seoul,Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19842-7_15","article-title":"Pixel-wise energy-biased abstention learning for anomaly segmentation on complex urban driving scenes","author":"Tian","year":"2022"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19806-9_29","article-title":"Densehybrid: Hybrid anomaly detection for dense open-set recognition","author":"Grci\u0107","year":"2022"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.01664","article-title":"Pixel-wise anomaly detection in complex driving scenes","author":"Biase","year":"2021"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00375","article-title":"Segment every out-of-distribution object","author":"Zhao","year":"2024"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00112","article-title":"Residual pattern learning for pixel-wise out-of-distribution detection in semantic segmentation","author":"Liu","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3419055"},{"article-title":"Learning transferable visual models from natural language supervision","year":"2021","author":"Radford","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"article-title":"WordNet a lexical database for English","volume-title":"Speech and Natural Language: Proceedings of a Workshop Held at Harriman, New York, February 23-26, 1992","author":"Miller","key":"ref9"},{"article-title":"Microsoft coco: Common objects in context","year":"2015","author":"Lin","key":"ref10"},{"article-title":"Deep residual learning for image recognition","year":"2015","author":"He","key":"ref11"},{"article-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","year":"2017","author":"Chen","key":"ref12"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2021","author":"Dosovitskiy","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"article-title":"Leveraging inductive bias in vit for medical image diagnosis","year":"2024","author":"Ha","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137099"},{"article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","year":"2021","author":"Jia","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref19","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19815-1_40","article-title":"Extract free dense labels from clip","author":"Zhou","year":"2022"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW63382.2024.00367","article-title":"Sam-clip: Merging vision foundation models towards semantic and spatial understanding","author":"Wang","year":"2024"},{"article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","year":"2023","author":"Yu","key":"ref21"},{"article-title":"Strong but simple: A baseline for domain generalized dense perception by clip-based transfer learning","year":"2024","author":"H\u00fcmmer","key":"ref22"},{"key":"ref23","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4783140","article-title":"Exploring the frontier of vision-language models: A survey of current methodologies and future directions","author":"Ghosh","year":"2024"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: A survey","author":"Zhang","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01631","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_3"},{"article-title":"Mta-clip: Language-guided semantic segmentation with mask-text alignment","year":"2024","author":"Das","key":"ref28"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00695","article-title":"Image segmentation using text and image prompts","author":"L\u00fcddecke","year":"2022"},{"article-title":"Learning to prompt segment anything models","year":"2024","author":"Huang","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78172-8_15"},{"article-title":"Uncertainty estimation and out-of-distribution detection for lidar scene semantic segmentation","year":"2024","author":"Shojaei","key":"ref32"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-59861-7_10","article-title":"Out-of-distribution detection for skin lesion images with deep isolation forest","author":"Li","year":"2020"},{"article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","year":"2018","author":"Hendrycks","key":"ref34"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00493","article-title":"Weakly-supervised video anomaly detection with robust temporal feature magnitude learning","author":"Tian","year":"2021"},{"article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","year":"2020","author":"Liang","key":"ref36"},{"article-title":"Training confidence-calibrated classifiers for detecting out-of-distribution samples","year":"2018","author":"Lee","key":"ref37"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00224","article-title":"Detecting the unexpected via image resynthesis","author":"Lis","year":"2019"},{"article-title":"This is not what i imagined: Error detection for semantic segmentation through visual dissimilarity","year":"2019","author":"Haldimann","key":"ref39"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-58452-8_9","article-title":"Synthesize then compare: Detecting failures and anomalies for semantic segmentation","author":"Xia","year":"2020"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00072","article-title":"Rba segmenting unknown regions rejected by all","author":"Nayal","year":"2023"},{"key":"ref42","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"article-title":"Placing objects in context via inpainting for out-of-distribution segmentation","year":"2024","author":"de Jorge","key":"ref43"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01042","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"article-title":"Negative label guided ood detection with pretrained vision-language models","year":"2024","author":"Jiang","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3454157"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00332"},{"article-title":"A review on deep learning techniques applied to semantic segmentation","year":"2017","author":"Garcia-Garcia","key":"ref48"},{"article-title":"Segmentmeifyoucan: A benchmark for anomaly segmentation","year":"2021","author":"Chan","key":"ref49"},{"key":"ref50","first-page":"1099","article-title":"Lost and found: detecting small road hazards for self-driving vehicles","volume-title":"2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Pinggera"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246989.pdf?arnumber=11246989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:14:22Z","timestamp":1765520062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246989","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}