Self-Supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species
Self-Supervised Learning for Panoptic Segmentation of Multiple Fruit Flower Species
复制标题
基于自监督学习的多果树花卉全景分割
DOI：
10.1109/lra.2022.3217000
复制
发表时间：
2022-09
影响因子：
5.2
通讯作者：
Abubakar Siddique;A. Tabb;Henry Medeiros
中科院分区：
文献类型：
--
作者：
Abubakar Siddique;A. Tabb;Henry Medeiros
使用手动生成的标签训练的卷积神经网络通常用于语义或实例分割。在精准农业中，自动化花卉检测方法使用监督模型和后处理技术，这些技术可能会随着花卉的外观和数据采集条件的变化而不一致。我们提出了一种自监督学习策略，使用自动生成的伪标签来增强分割模型对不同花卉物种的敏感性。我们采用数据增强和细化方法来提高模型预测的准确性。然后将增强的语义预测转换为全景伪标签，以迭代地训练多任务模型。可以使用现有的后处理方法来改进自监督模型预测，以进一步提高其准确性。对多物种果树花数据集的评估表明，我们的方法优于最先进的模型，无需计算昂贵的后处理步骤，为花检测应用提供了新的基线。
Convolutional neural networks trained using manually generated labels are commonly used for semantic or instance segmentation. In precision agriculture, automated flower detection methods use supervised models and post-processing techniques that may not perform consistently as the appearance of the flowers and the data acquisition conditions vary. We propose a self-supervised learning strategy to enhance the sensitivity of segmentation models to different flower species using automatically generated pseudo-labels. We employ a data augmentation and refinement approach to improve the accuracy of the model predictions. The augmented semantic predictions are then converted to panoptic pseudo-labels to iteratively train a multi-task model. The self-supervised model predictions can be refined with existing post-processing approaches to further improve their accuracy. An evaluation on a multi-species fruit tree flower dataset demonstrates that our method outperforms state-of-the-art models without computationally expensive post-processing steps, providing a new baseline for flower detection applications.