Metraipolis › archive › dc_bcf0dee3abd1
MAVISEG: Manifold Propagation and Visual Prototypes for Zero-Shot Open-Vocabulary Segmentation in Diffusion Transformers — arXiv:2608.05878
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05878
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:36:21.824Z
- SHA-256 of the archived text
4b7f871b3f16cba6e5883e75dd4caeb7283627560b3ac583bf88f8d464188b36- Stable URL of this page
https://metraipolis.com/documento/dc_bcf0dee3abd1
How to cite
MAVISEG: Manifold Propagation and Visual Prototypes for Zero-Shot Open-Vocabulary Segmentation in Diffusion Transformers — arXiv:2608.05878 — arXiv (en), https://arxiv.org/abs/2608.05878 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bcf0dee3abd1 (Metraipolis archive dc_bcf0dee3abd1, sha256 4b7f871b3f16cba6e5883e75dd4caeb7283627560b3ac583bf88f8d464188b36)
BibTeX
@misc{dcbcf0dee3abd1,
title = {MAVISEG: Manifold Propagation and Visual Prototypes for Zero-Shot Open-Vocabulary Segmentation in Diffusion Transformers — arXiv:2608.05878},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05878},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bcf0dee3abd1; sha256 4b7f871b3f16cba6e5883e75dd4caeb7283627560b3ac583bf88f8d464188b36},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05878. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-image diffusion transformers learn about objects and scenes by learning to generate them, making them strong candidates for training-free zero-shot open-vocabulary semantic segmentation. State-of-the-art attribution methods score each pixel independently, comparing its features against a fixed text-derived class representation, whether as an output-space similarity or as a cross-attention weight. This discards structured signals the model itself exposes: the temporal structure of the generative trajectory, the visual appearance statistics of each concept, and the image's own pairwise feature geometry. We present MAVISEG, a training-free refinement layer that recovers these signals. Because its operators consume only a pixel-by-concept score field and a pixel feature space, MAVISEG is capture-agnostic rather than tied to one attribution method. Across six benchmarks it achieves the strongest overall results among training-free methods, including the best mIoU on every benchmark. Interestingly, gains are largest where the initial capture is weakest, and individual operators contribute depending on the noise in the field they refine. Our results indicate that diffusion transformers carry more concept-level information than current attribution methods recover, and that much of it is lost on the way to the mask rather than absent from the model. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05878 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T10:23:31.030Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).