Abstract
Analyzing underwater fish imagery is critical for ecological monitoring but remains difficult due to visual degradation and costly annotations. We introduce FishDetector-R1, a unified MLLM-based framework for fish detection, segmentation, and counting under weak supervision. On the DeepFish dataset, our framework achieves substantial gains over baselines, improving AP by 20% and mIoU by 10%, while reducing MAE by 30% and GAME by 35%. These improvements stem from two key components: a novel detect-to-count prompt that enforces spatially consistent detections and counts, and Reinforcement Learning from Verifiable Reward (RLVR) with a complementary scalable paradigm leveraging sparse point labels. Ablation studies further validate the effectiveness of this reward design. Moreover, the improvement generalizes well to other underwater datasets, confirming strong cross-domain robustness. Overall, FishDetector-R1 provides a reliable and scalable solution for accurate marine visual understanding via weak supervision. The project page for FishDetector-R1 is this https URL.
Abstract (translated)
分析水下鱼类图像对于生态监测至关重要，但由于视觉退化和高昂的标注成本，这一过程依然充满挑战。为此，我们提出了FishDetector-R1，这是一个基于多模态大型语言模型（MLLM）的统一框架，用于在弱监督条件下进行鱼类检测、分割和计数。 在DeepFish数据集上，我们的框架相较于基线方法实现了显著改进：平均精度（AP）提高了20%，平均交并比（mIoU）提升了10%，绝对平均误差（MAE）减少了30%，以及全局平均误差（GAME）降低了35%。这些改进主要归功于两个关键组成部分： - 一种新颖的检测至计数提示，该提示强制执行空间一致的检测和计数； - 基于可验证奖励的强化学习（RLVR），并采用了一种补充的大规模范式，利用稀疏点标签。 消融实验进一步证实了这种奖赏设计的有效性。此外，改进还很好地推广到了其他水下数据集上，确认了强大的跨域鲁棒性。 总体而言，FishDetector-R1为通过弱监督实现准确的海洋视觉理解提供了一个可靠且可扩展的解决方案。有关FishDetector-R1项目的更多信息，请访问此项目页面：[https URL]（请将链接替换为您实际提供的URL）。
URL
https://arxiv.org/abs/2512.05996
