MARIS：海洋开放词表实例分割
MARIS: Marine Open-Vocabulary Instance Segmentation
针对水下场景的开放词表实例分割，提出几何先验增强模块（GPEM）利用部件级结构线索保持退化视觉下的物体一致性，以及语义对齐注入机制（SAIM）用域特定先验丰富语言嵌入以识别未见类别，为跨域开放词表分割提供了可复用的设计思路。
原文依据 we propose a unified framework with two complementary components
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有大多数水下实例分割方法受限于闭词表预测，限制了其识别新海洋类别的能力。为支持评估，我们引入了MARIS（海洋开放词表实例分割），这是首个面向水下开放词表（OV）实例分割（UOVIS）的大规模细粒度基准，包含有限的已见类别和多样的未见类别。尽管开放词表实例分割在自然图像上已展现出潜力，但我们的分析表明，迁移到水下场景时会遭受严重的视觉退化（如颜色衰减）以及由于缺乏水下类别定义而导致的语义错位。为解决这些问题，我们提出了一个由两个互补组件构成的统一框架。几何先验增强模块（GPEM）利用稳定的部件级和结构线索，在退化视觉条件下保持物体一致性。语义对齐注入机制（SAIM）用域特定先验丰富语言嵌入，缓解语义歧义并提升对未见类别的识别。实验表明，我们的框架在MARIS上的域内和跨域设置中均持续优于现有的开放词表基线，为未来水下感知研究奠定了坚实基础。本文代码可在Github上找到。
英文原文摘要 1411 字符
Most existing underwater instance segmentation approaches are constrained by close-vocabulary prediction, limiting their ability to recognize novel marine categories. To support evaluation, we introduce **MARIS** (_Marine Open-Vocabulary Instance Segmentation_), the first large-scale fine-grained benchmark for underwater Open-Vocabulary (OV) Instance segmentation (UOVIS), featuring a limited set of seen categories and diverse unseen categories. Although OV instance segmentation has shown promise on natural images, our analysis reveals that transfer to underwater scenes suffers from severe visual degradation (e.g., color attenuation) and semantic misalignment caused by lack underwater class definitions. To address these issues, we propose a unified framework with two complementary components. The Geometric Prior Enhancement Module (**GPEM**) leverages stable part-level and structural cues to maintain object consistency under degraded visual conditions. The Semantic Alignment Injection Mechanism (**SAIM**) enriches language embeddings with domain-specific priors, mitigating semantic ambiguity and improving recognition of unseen categories. Experiments show that our framework consistently outperforms existing OV baselines both In-Domain and Cross-Domain setting on MARIS, establishing a strong foundation for future underwater perception research. The code of this paper can be found in Github.