Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract)
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41242-41243
DOI: 10.1609/aaai.v40i48.42228 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Suin Kim und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Recent advances in diffusion-based models have significantly broadened their scope, extending well beyond image generation to encompass zero-shot segmentation tasks. In this work, we introduce a novel, training-free approach that harnesses both self- and cross-attention maps to achieve highly detailed hair segmentation. Our method demonstrates remarkable efficacy in producing fine-grained results without the need for additional training.
Zitieren
APA
Kim, S., Lee, J., Kang, M., Cha, D., & Ahn, S. (2026). Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41242-41243. https://doi.org/10.1609/aaai.v40i48.42228
Vancouver
Kim S, Lee J, Kang M, Cha D, Ahn S. Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41242-41243. doi:10.1609/aaai.v40i48.42228
BibTeX
@article{Kim2026,
author = {Kim, Suin and Lee, Jihoon and Kang, Moonsung and Cha, Doheun and Ahn, Sangtae},
title = {Spatially-Guided Self-Attention Refinement for Zero-Shot Hair Segmentation (Student Abstract)},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41242--41243},
doi = {10.1609/aaai.v40i48.42228}
}
EUVIMED