QCN让胶囊网络提速5倍，适合实时应用。
Quick-CapsNet (QCN): A fast alternative to Capsule Networks
- 减少胶囊数量以加快推理速度
- 在多个数据集上推理速度提升5倍
- 适合需要快速响应的实时场景
胶囊网络（CapsNet）的基本计算单元是胶囊（一组构成向量的神经元），相比传统卷积神经网络（CNN）在处理重叠数字和仿射变换时表现更优。但其训练与测试速度较慢，限制了实际应用。本文提出快速胶囊网络（Quick-CapsNet, QCN），通过减少胶囊数量实现加速，仅损失少量准确率。在MNIST、F-MNIST、SVHN和Cifar-10数据集上，推理速度提升5倍。此外，采用更强的解码器进一步优化性能。
原文摘要 · Abstract (English)
The basic computational unit in Capsule Network (CapsNet) is a capsule (vs. neurons in Convolutional Neural Networks (CNNs)). A capsule is a set of neurons, which form a vector. CapsNet is used for supervised classification of data and has achieved state-of-the-art accuracy on MNIST digit recognition dataset, outperforming conventional CNNs in detecting overlapping digits. Moreover, CapsNet shows higher robustness towards affine transformation when compared to CNNs for MNIST datasets. One of the drawbacks of CapsNet, however, is slow training and testing. This can be a bottleneck for applications that require a fast network, especially during inference. In this work, we introduce Quick-CapsNet (QCN) as a fast alternative to CapsNet, which can be a starting point to develop CapsNet for fast real-time applications. QCN builds on producing a fewer number of capsules, which results in a faster network. QCN achieves this at the cost of marginal loss in accuracy. Inference is 5x faster on MNIST, F-MNIST, SVHN and Cifar-10 datasets. We also further enhanced QCN by employing a more powerful decoder instead of the default decoder to further improve QCN.
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。