Discriminative feature learning for underwater fish recognition
Discriminative feature learning for underwater fish recognition
复制标题
DOI：
10.1117/1.jei.30.2.023020
复制
发表时间：
2021-03
影响因子：
1.1
通讯作者：
Zhixue Zhang;Xiujuan Du;Long Jin;Duoliang Han;Chong Li;Xin Liu
中科院分区：
文献类型：
--
作者：
Zhixue Zhang;Xiujuan Du;Long Jin;Duoliang Han;Chong Li;Xin Liu
抽象的。水下鱼类识别是鱼类资源评估和海洋生态系统研究中的一项重要任务。机器学习技术已经被应用于从水下图像训练高性能的鱼类识别模型。然而，水下图像往往包含非常嘈杂的背景，阻碍了准确的识别模型的训练。传统方法利用手工特征来训练传统分类器。这些方法通常具有识别精度低和对大规模数据集的可扩展性有限的缺点。虽然已经提出了深度学习方法，但使用嘈杂的水下图像进行学习的挑战尚未完全解决。我们提出了一个判别式特征学习（DFL）框架，以训练准确的鱼类识别模型在嘈杂的水下图像。通过利用对比学习的思想，DFL鼓励模型为不同类别的图像学习更多的区分性特征，并为同一类别的图像学习相似的特征。为了更好地解决噪声背景问题，DFL还利用了一种称为注意力抑制的正则化技术，以防止模型对噪声背景过于关注。在三个基准数据集上的实验结果验证了DFL优于当前最先进的深度学习方法的上级性能。
Abstract. Underwater fish recognition is an important task in fish stock assessment and marine ecosystem studies. Machine learning techniques have been applied to train high-performance fish recognition models from underwater images. However, underwater images often contain extremely noisy backgrounds, hindering the training of accurate recognition models. Traditional methods exploit handcrafted features to train traditional classifiers. These methods often suffer from low recognition accuracy and limited scalability to large-scale datasets. While deep learning approaches have been proposed, the challenge of learning with noisy underwater images has not yet been fully addressed. We propose a discriminative feature learning (DFL) framework to train accurate fish recognition models on noisy underwater images. By leveraging the idea of contrastive learning, DFL encourages the model to learn more discriminative features for images in different classes and similar features for images in the same class. To better address the noisy background problem, DFL also utilizes a regularization technique called attention suppression to prevent the model from paying too much attention to the noisy background. Experimental results on three benchmark datasets validate the superior performance of DFL over the current state-of-the-art deep learning approaches.