ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements

Cite

Text

Aydin et al. "ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.

Markdown

[Aydin et al. "ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/aydin2025cvprw-itaclip/)

BibTeX

@inproceedings{aydin2025cvprw-itaclip,
  title     = {{ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements}},
  author    = {Aydin, M. Arda and Çirpar, Efe Mert and Abdinli, Elvin and Unal, Gozde and Sahin, Yusuf Hüseyin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2025},
  pages     = {4142-4152},
  url       = {https://mlanthology.org/cvprw/2025/aydin2025cvprw-itaclip/}
}