Zhou Heng, Dong Jiuqing, Han Shujie, Chung Seyeon, Ali Hassan, Kim Sangcheol
Department of Electronics and Information Engineering, Jeonbuk National University, 54896, Jeonju, Republic of Korea.
Core Research Institute of Intelligent Robots, Jeonbuk National University, 54896, Jeonju, Republic of Korea.
Sci Rep. 2025 Jun 4;15(1):19706. doi: 10.1038/s41598-025-05113-x.
Pig instance segmentation is a critical component of smart pig farming, serving as the basis for advanced applications such as health monitoring and weight estimation. However, existing methods typically rely on large volumes of precisely labeled mask data, which are both difficult and costly to obtain, thereby limiting their scalability in real-world farming environments. To address this challenge, this paper proposes a novel approach that leverages simpler box annotations as supervisory information to train a pig instance segmentation network. In contrast to traditional methods, which depend on expensive mask annotations, our approach adopts a weakly supervised learning paradigm that reduces annotation cost. Specifically, we enhance the loss function of an existing weakly supervised instance segmentation model to better align with the requirements of pig instance segmentation. We conduct extensive experiments to compare the performance of the proposed method that only uses box annotations, with that of five fully supervised models requiring mask annotations and two weakly supervised baselines. Experimental results demonstrate that our method outperforms all existing weakly supervised approaches and three out of five fully supervised models. Moreover, compared with fully supervised methods, our approach exhibits only a 3% performance gap in mask prediction. Given that annotating a box takes merely 26 seconds, whereas annotating a mask requires 94 seconds, this minor accuracy trade-off is practically negligible. These findings highlight the value of employing box annotations for pig instance segmentation, offering a more cost-effective and scalable alternative without compromising performance. Our work not only advances the field of pig instance segmentation but also provides a viable pathway to deploy smart farming technologies in resource-limited settings, thereby contributing to more efficient and sustainable agricultural practices.
猪实例分割是智能养猪的关键组成部分，是健康监测和体重估计等高级应用的基础。然而，现有方法通常依赖大量精确标注的掩码数据，这些数据获取困难且成本高昂，从而限制了它们在实际养殖环境中的可扩展性。为应对这一挑战，本文提出了一种新颖的方法，该方法利用更简单的边界框标注作为监督信息来训练猪实例分割网络。与依赖昂贵掩码标注的传统方法不同，我们的方法采用了弱监督学习范式，降低了标注成本。具体而言，我们增强了现有弱监督实例分割模型的损失函数，以更好地符合猪实例分割的要求。我们进行了广泛的实验，将仅使用边界框标注的所提方法的性能与五个需要掩码标注的全监督模型以及两个弱监督基线的性能进行比较。实验结果表明，我们的方法优于所有现有的弱监督方法以及五个全监督模型中的三个。此外，与全监督方法相比，我们的方法在掩码预测方面仅表现出3%的性能差距。鉴于标注一个边界框仅需26秒，而标注一个掩码需要94秒，这种微小的精度权衡实际上可以忽略不计。这些发现凸显了使用边界框标注进行猪实例分割的价值，提供了一种更具成本效益且可扩展的替代方案，同时不影响性能。我们的工作不仅推动了猪实例分割领域的发展，还为在资源有限的环境中部署智能养殖技术提供了一条可行途径，从而有助于实现更高效和可持续的农业实践。
