arXiv cs.AI· Meng Liang, Fucheng Wang, Lang Zhao, Jun Chen, Ziying Li, Yuxiang Zhao, Haozhuang Chi, Wenkai Fang, Qiong Zhou, Junlin Yang, Jinming Wu·· 2 小时前AI 评分32
FSVL：面向长江中游易混淆鱼种可解释识别与知识生成的分类学快慢视觉-语言协同框架
FSVL: Taxonomic Fast-Slow Vision-to-Language Collaborative Framework for Interpretable Confusable Fish Species Identification and Knowledge Generation in the Middle Yangtze River
AI 导读
FSVL 是一个结合视觉识别与大语言模型 RAG 的快慢双通路框架，用于长江中游 51 种鱼类的细粒度识别。轻量 ResNet50 快通路初分类，慢通路用 YOLOv8n 检测头部、背鳍、尾部等关键形态区域做精细鉴别，并接入经 LoRA 微调的 Qwen3-14B 生成领域知识。
正文 · 原文
Authors:Meng Liang, Fucheng Wang, Lang Zhao, Jun Chen, Ziying Li, Yuxiang Zhao, Haozhuang Chi, Wenkai Fang, Qiong Zhou, Junlin Yang, Jinming Wu
Abstract:The Yangtze River Basin is a critical region for freshwater biodiversity conservation. The implementation of the Yangtze River Ten-Year Fishing Ban has increased the importance of effective aquatic biodiversity monitoring and species-level identification. However, fine-grained identification of closely related freshwater fish species remains challenging due to subtle morphological differences. Existing deep learning methods often struggle to balance classification accuracy and inference efficiency, while LLMs may generate unsupported information when producing specialized biological knowledge. To address these challenges, this study proposes FSVL, a fast-slow dual-pathway framework integrating visual recognition with LLM-based Retrieval-Augmented Generation (RAG). A lightweight ResNet50 fast path performs preliminary classification across 51 fish species in the Middle Yangtze River Basin and routes predefined groups of easily confused species to a slow path for refined identification. Guided by taxonomic criteria, the slow path uses YOLOv8n to detect key morphological regions, including the head, dorsal fin, and tail, leveraging morphometric and outline traits to improve discrimination among closely related species. The framework further integrates a retrieval-enhanced Qwen3-14B backend, using soft tokens and Low-Rank Adaptation (LoRA) for parameter-efficient domain knowledge generation. On the evaluated test set of 607 images, the fast classifier achieved 99.67% accuracy, whereas the cascade corrected the two errors, yielding 100.00% overall accuracy; further validation on independent specimens and external conditions remains needed. Across 255 knowledge generation samples, scientific name accuracy rises from 91.37% to 100.00%, genus accuracy from 90.20% to 98.82%, and ROUGE-L from 0.335 to 0.655, supporting intelligent biodiversity monitoring and fisheries management.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.31880 [cs.CV] |
| (or arXiv:2610.31880v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31880 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Liang Meng [view email]
[v1]
Thu, 22 Oct 2026 20:22:31 UTC (5,470 KB)
来源：arXiv cs.AI · arxiv.org