# Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation

Source: [Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation](<https://www.sota2.com/research/paper/6a0a9d2bdbc836b87d82b4c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-19T05:00:13.117Z

Authors: Chenhao Wang, Yingrui Ji, Yu Meng, Yao Zhu

Published: 2026-05-15T13:27:01.000Z

## Abstract

Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained descriptions are typically encoded as holistic sentences that entangle multiple semantic units. We propose a Decomposed Vision-Language Alignment framework that explicitly factorizes textual prompts into a concept token and multiple attribute tokens, enabling separate cross-modal interactions for each semantic unit. At the feature level, we introduce a Feature-Gated Cross-Attention module that generates attribute-specific gating maps to fuse information in a multiplicative manner, effectively enforcing compositional semantics. At the scoring level, per-token similarities are aggregated in log-space, producing a stable and interpretable compositional matching. The method can be seamlessly integrated into existing transformer-based segmentation architectures and significantly improves generalization to unseen attribute-category compositions in fine-grained open-vocabulary segmentation benchmarks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Open-vocabulary Segmentation on UBC](<https://www.sota2.com/research/sota/open-vocabulary-segmentation-on-ubc.md>): Open-Vocabulary Segmentation; UBC; AP Unseen: 7.1.

- [Open-vocabulary Segmentation on PACO](<https://www.sota2.com/research/sota/open-vocabulary-segmentation-on-paco.md>): Open-Vocabulary Segmentation; PACO; AP Unseen: 39.2.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.15942>)

[PDF](<https://arxiv.org/pdf/2605.15942.pdf>)
