解决量子卷积网络梯度消失问题，实现98.7%图像分类准确率。
Beyond Barren Plateaus: A Scalable Quantum Convolutional Architecture for High-Fidelity Image Classification
- 采用局部代价函数与张量网络初始化，有效缓解梯度消失。
- 在MNIST上达到98.7%准确率，较基线52.32%大幅提升。
- 参数效率更高，所需参数量仅为经典CNN的O(log N)。
尽管量子卷积神经网络（QCNN）为量子机器学习提供了理论范式，但其实际应用受限于梯度指数级消失的“荒原悬崖”问题，且性能远低于经典模型。本文提出一种新型QCNN架构，结合局部代价函数和硬件高效的张量网络初始化策略，可严格缓解荒原悬崖现象。我们在MNIST数据集上评估该可扩展的QCNN，实现了显著性能提升。通过解决梯度消失问题，优化后的QCNN达到了98.7%的分类准确率，远超未缓解模型的52.32%基线表现。此外，我们还提供实证证据表明其具有参数效率优势：仅需比等效经典CNN少$/mathcal{O}( ext{log }N)$的可训练参数即可实现>95%的收敛。本工作弥合了理论量子优势与实际应用之间的差距，为无需陷入损失景观集中化的量子计算机视觉任务提供可扩展框架。
原文摘要 · Abstract (English)
While Quantum Convolutional Neural Networks (QCNNs) offer a theoretical paradigm for quantum machine learning, their practical implementation is severely bottlenecked by barren plateaus -- the exponential vanishing of gradients -- and poor empirical accuracy compared to classical counterparts. In this work, we propose a novel QCNN architecture utilizing localized cost functions and a hardware-efficient tensor-network initialization strategy to provably mitigate barren plateaus. We evaluate our scalable QCNN on the MNIST dataset, demonstrating a significant performance leap. By resolving the gradient vanishing issue, our optimized QCNN achieves a classification accuracy of 98.7\%, a substantial improvement over the baseline QCNN accuracy of 52.32\% found in unmitigated models. Furthermore, we provide empirical evidence of a parameter-efficiency advantage, requiring $\mathcal{O}(\log N)$ fewer trainable parameters than equivalent classical CNNs to achieve $>95\%$ convergence. This work bridges the gap between theoretical quantum utility and practical application, providing a scalable framework for quantum computer vision tasks without succumbing to loss landscape concentration.
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。