量子掩码自编码器提升图像重建与分类精度。
Quantum Masked Autoencoders for Vision Learning
- 在量子态中学习被遮蔽的图像特征，而非经典嵌入。
- 在MNIST类图像上实现平均12.86%更高的分类准确率。
- 适合对量子机器学习与视觉任务感兴趣的科研人员。
经典自编码器广泛用于学习输入数据的特征。为提升特征学习能力，经典掩码自编码器在部分数据被遮蔽的情况下学习原始样本特征。尽管已有量子自编码器，但尚无能利用量子计算优势的量子掩码自编码器设计与实现。本文提出量子掩码自编码器（QMAE），可在量子态中有效学习数据样本的缺失特征，而非依赖经典嵌入。实验表明，该架构能重建被遮蔽的图像，并在MNIST系列图像中实现更高视觉保真度。评估显示，在存在遮蔽的情况下，QMAE的分类准确率平均比现有最优量子自编码器高出12.86%。
原文摘要 · Abstract (English)
Classical autoencoders are widely used to learn features of input data. To improve the feature learning, classical masked autoencoders extend classical autoencoders to learn the features of the original input sample in the presence of masked-out data. While quantum autoencoders exist, there is no design and implementation of quantum masked autoencoders that can leverage the benefits of quantum computing and quantum autoencoders. In this paper, we propose quantum masked autoencoders (QMAEs) that can effectively learn missing features of a data sample within quantum states instead of classical embeddings. We showcase that our QMAE architecture can learn the masked features of an image and can reconstruct the masked input image with improved visual fidelity in MNIST-family images. Experimental evaluation highlights that QMAE can significantly outperform (12.86% on average) in classification accuracy compared to state-of-the-art quantum autoencoders in the presence of masks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。