arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.01234cs.CVcs.LG
收藏

基于学习恢复原型的单次图像分类

One-Shot Image Classification by Learning to Restore Prototypes

National University of Singapore(新加坡国立大学)

Wanqi Xue, Wei Wang

摘要:

单次图像分类的目标是在数据集上训练图像分类器,每个类别只有一个图像。这对于现代深度神经网络来说是一个挑战,因为每个类通常需要数百或数千张图像。在本文中,我们采用度量学习这个问题,它已被应用于少镜头和多镜头图像分类通过比较测试图像和每个类的中心之间的距离在特征空间。然而,对于单次学习,现有的度量学习方法将遭受性能差,因为单个训练图像可能不代表类。例如,如果图像远离特征空间中的类中心,则基于度量学习的算法不太可能对测试图像做出正确的预测,因为决策边界被该噪声图像移位。为了解决这个问题,我们提出了一个简单而有效的回归模型,表示为RestoreNet,它学习图像特征上的类不可知变换,以将图像移动到更接近特征空间中的类中心。实验表明,RestoreNet在广泛的数据集上获得了优于最先进方法的性能。此外,RestoreNet可以很容易地与其他方法结合,以实现进一步的改进。

英文摘要:

One-shot image classification aims to train image classifiers over the dataset with only one image per category. It is challenging for modern deep neural networks that typically require hundreds or thousands of images per class. In this paper, we adopt metric learning for this problem, which has been applied for few- and many-shot image classification by comparing the distance between the test image and the center of each class in the feature space. However, for one-shot learning, the existing metric learning approaches would suffer poor performance because the single training image may not be representative of the class. For example, if the image is far away from the class center in the feature space, the metric-learning based algorithms are unlikely to make correct predictions for the test images because the decision boundary is shifted by this noisy image. To address this issue, we propose a simple yet effective regression model, denoted by RestoreNet, which learns a class agnostic transformation on the image feature to move the image closer to the class center in the feature space. Experiments demonstrate that RestoreNet obtains superior performance over the state-of-the-art methods on a broad range of datasets. Moreover, RestoreNet can be easily combined with other methods to achieve further improvement.

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。

↑