Earth2Ocean：无需额外训练的水下开放词汇分割框架

View PDF HTML (experimental)

Abstract:Accurate segmentation of marine organisms is vital for biodiversity monitoring and ecological assessment, yet existing datasets and models remain largely limited to terrestrial scenes. To bridge this gap, we introduce \textbf{AquaOV255}, the first large-scale and fine-grained underwater segmentation dataset containing 255 categories and over 20K images, covering diverse categories for open-vocabulary (OV) evaluation. Furthermore, we establish the first underwater OV segmentation benchmark, \textbf{UOVSBench}, by integrating AquaOV255 with five additional underwater datasets to enable comprehensive evaluation. Alongside, we present \textbf{Earth2Ocean}, a training-free OV segmentation framework that transfers terrestrial vision--language models (VLMs) to underwater domains without any additional underwater training. Earth2Ocean consists of two core components: a Geometric-guided Visual Mask Generator (\textbf{GMG}) that refines visual features via self-similarity geometric priors for local structure perception, and a Category-visual Semantic Alignment (\textbf{CSA}) module that enhances text embeddings through multimodal large language model reasoning and scene-aware template construction. Extensive experiments on the UOVSBench benchmark demonstrate that Earth2Ocean achieves significant performance improvement on average while maintaining efficient inference.

Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2511.07923 [cs.CV]
	(or arXiv:2511.07923v3 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2511.07923 arXiv-issued DOI via DataCite

Submission history

From: Bingyu Li [view email]
[v1] Tue, 11 Nov 2025 07:22:56 UTC (6,604 KB)
[v2] Tue, 17 Mar 2026 09:16:24 UTC (6,604 KB)
[v3] Sat, 10 Oct 2026 04:49:40 UTC (3,771 KB)