Metraipolis › archive › dc_dc73e14799e5

Generative Semantic Segmentation via an Observable Semantic-Image Interface and Hierarchical Generator Evidence Alignment — arXiv:2608.11537

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.11537
License (as archived): CC0-1.0
Archived: 2026-10-19T05:15:54.376Z
SHA-256 of the archived text: d88d01ce395c969bcb898924e46b46f63ab59a1d3440374493f810a10e638ce4
Stable URL of this page: https://metraipolis.com/documento/dc_dc73e14799e5

How to cite

Generative Semantic Segmentation via an Observable Semantic-Image Interface and Hierarchical Generator Evidence Alignment — arXiv:2608.11537 — arXiv (en), https://arxiv.org/abs/2608.11537 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc73e14799e5 (Metraipolis archive dc_dc73e14799e5, sha256 d88d01ce395c969bcb898924e46b46f63ab59a1d3440374493f810a10e638ce4)

BibTeX

@misc{dcdc73e14799e5,
  title = {Generative Semantic Segmentation via an Observable Semantic-Image Interface and Hierarchical Generator Evidence Alignment — arXiv:2608.11537},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11537},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc73e14799e5; sha256 d88d01ce395c969bcb898924e46b46f63ab59a1d3440374493f810a10e638ce4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11537. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Generative semantic segmentation exposes structured predictions as images, but direct color decoding is susceptible to color drift and boundary mixing, whereas latent-feature decoders that predict a separate output distribution may relegate the rendered image to an intermediate visualization. We present Semantic Prism, a conditional semantic-image generation-and-refinement framework with deterministic inference. A diffusion-distilled one-step generator renders a semantic RGB image; per-pixel distances from the rendered colors to a fixed class-color codebook define an explicit probabilistic interface. Hierarchical Generator Evidence Alignment spatially aligns multi-level generator features and uses a zero-initialized output projection to predict an additive residual in the interface logit space, retaining the image-defined interface as the reference for the final distribution. The interface and refined distributions further enable Contextual Interface--Hierarchy Disagreement (C-IHD), a fixed readout for ranking remaining pixel errors without an auxiliary predictor or additional forward pass. On the 500-image Cityscapes validation set, Semantic Prism achieves 72.07% mean intersection over union, 11.39 mIoU points above direct-interface decoding, with 0.41% expected calibration error. Matched-capacity ablations over three seeds support the benefit of jointly aligned multi-level evidence. A separately trained model attains 62.22% mIoU on BDD100K, while the Cityscapes-trained model reaches 46.89\% mIoU under source-frozen transfer to the Adverse Conditions Dataset with Correspondences, without target-domain adaptation. Across all three datasets, C-IHD consistently improves the area under the precision--recall curve for pixel-error ranking over maximum softmax probability on the same segmentation predictions; on ACDC, it raises AUPR from 0.6580 to 0.7557.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Image and Video Processing (eess.IV).
Pagina del lavoro: https://arxiv.org/abs/2608.11537 — 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 2026-10-19T05:08:46.698Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).