Metraipolis › archive › dc_321742e9deb0
ODC: Orthogonal Drift Correction for Improved Text-to-Image Semantic Alignment at Inference — arXiv:2611.00819
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00819
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:24:33.701Z
- SHA-256 of the archived text
6580b9249c63cd727842e3c0639c6b3d25a780d842798747a0e0daf16a9f1d2b- Stable URL of this page
https://metraipolis.com/documento/dc_321742e9deb0
How to cite
ODC: Orthogonal Drift Correction for Improved Text-to-Image Semantic Alignment at Inference — arXiv:2611.00819 — arXiv (en), https://arxiv.org/abs/2611.00819 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_321742e9deb0 (Metraipolis archive dc_321742e9deb0, sha256 6580b9249c63cd727842e3c0639c6b3d25a780d842798747a0e0daf16a9f1d2b)
BibTeX
@misc{dc321742e9deb0,
title = {ODC: Orthogonal Drift Correction for Improved Text-to-Image Semantic Alignment at Inference — arXiv:2611.00819},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00819},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_321742e9deb0; sha256 6580b9249c63cd727842e3c0639c6b3d25a780d842798747a0e0daf16a9f1d2b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00819. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Text-to-image models have achieved remarkable success in generating high-quality images from textual descriptions. However, they often struggle with "semantic drift," where the generated output fails to precisely align with complex or nuanced text prompts. While recent approaches have attempted to address semantic errors regarding attribute binding or object presence, there remains a gap for a more holistic method that addresses these issues by directly refining the text embeddings of the initial user prompt. In this work, we introduce Orthogonal Drift Correction (ODC), an inference-time guidance method designed to mitigate semantic drift without requiring model retraining or additional user inputs. ODC guides image generation through a two-stage process. In the first stage, it identifies the semantic drift by evaluating the initially generated image against the user prompt in a shared vision-language embedding space. It then isolates the component of this drift vector that is orthogonal to the prompt's direction and translates it back into text via a vocabulary-based surrogate mechanism. In the second stage, it produces refined text conditioning for a second generation pass by feeding both the initial text embedding and the re-embedded drift representation into an adaptive rank-reduced concept removal module. Our experiments demonstrate that ODC consistently improves prompt-image alignment, increasing CLIP scores by up to 5.4% over the baseline on the COALBench-300 and PartiPrompts benchmarks. Furthermore, on the T2I-CompBench complex subset, ODC improves the average 3-in-1 score by 4.5% over the competing methods. As a plug-and-play module, ODC offers a practical and efficient method for improving the reliability of text-to-image models. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.00819 — 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 2026-11-03T18:10:08.021Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).