arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.08995cs.CV
收藏

简单而有效的特定领域图像无监督分类:以真菌图像为例

Simple but Effective Unsupervised Classification for Specified Domain Images: A Case Study on Fungi Images

School of Engineering, Dali University(大理大学工程学院);Institute of Eastern-Himalaya Biodiversity Research, Dali University(大理大学东喜马拉雅生物多样性研究所)

Zhaocong liu, Fa Zhang, Lin Cheng, Huanxi Deng, Xiaoyan Yang, Zhenyu Zhang, Chichun Zhou

AI总结:

提出一种无需监督的分类方法,通过两步特征降维、多聚类投票和事后标注,在真菌图像上达到94.1%和96.7%的准确率,减少对预标注数据的依赖。

摘要:

高质量标注数据集对于深度学习至关重要。传统的人工标注方法不仅成本高昂且效率低下,而且在需要专家知识的专业领域中也面临挑战。自监督方法尽管利用未标注数据进行特征提取,但仍需数百或数千个标注实例来引导模型进行有效的专业图像分类。当前的无监督学习方法无需事先标注即可提供自动分类,但往往在准确性上有所妥协。因此,对于缺乏标注数据的专业领域图像,高效获取高质量标注数据集仍然是一个紧迫的挑战。为解决此问题,本文提出了一种包含三个关键思想的无需监督分类方法:1)利用预训练模型和流形学习进行两步特征降维;2)采用多种聚类算法的投票机制;3)事后而非事先的人工标注。该方法在分类准确性上优于监督方法,如真菌图像数据所示,在公共和私有数据集上分别达到94.1%和96.7%的准确率。所提出的无监督分类方法减少了对预标注数据集的依赖,实现了数据分类的闭环。该方法的简单易用性也将为各领域研究人员构建数据集带来便利,促进人工智能在专业领域图像中的应用。

英文摘要:

High-quality labeled datasets are essential for deep learning. Traditional manual annotation methods are not only costly and inefficient but also pose challenges in specialized domains where expert knowledge is needed. Self-supervised methods, despite leveraging unlabeled data for feature extraction, still require hundreds or thousands of labeled instances to guide the model for effective specialized image classification. Current unsupervised learning methods offer automatic classification without prior annotation but often compromise on accuracy. As a result, efficiently procuring high-quality labeled datasets remains a pressing challenge for specialized domain images devoid of annotated data. Addressing this, an unsupervised classification method with three key ideas is introduced: 1) dual-step feature dimensionality reduction using a pre-trained model and manifold learning, 2) a voting mechanism from multiple clustering algorithms, and 3) post-hoc instead of prior manual annotation. This approach outperforms supervised methods in classification accuracy, as demonstrated with fungal image data, achieving 94.1% and 96.7% on public and private datasets respectively. The proposed unsupervised classification method reduces dependency on pre-annotated datasets, enabling a closed-loop for data classification. The simplicity and ease of use of this method will also bring convenience to researchers in various fields in building datasets, promoting AI applications for images in specialized domains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑