轻量增强版胶囊网络，速度更快、更准且抗变换能力强。
LE-CapsNet: A Light and Enhanced Capsule Network
- 用380万参数设计轻量化胶囊网络，结构优化提升效率。
- CIFAR-10上达76.73%准确率，推理速度比原胶囊网络快4倍。
- 对仿射变换图像识别更鲁棒，AffNIST上准确率达94.3%。
胶囊网络（CapsNet）相比卷积神经网络（CNN）在检测重叠类别图像和变换后图像方面具有优势。然而，由于结构差异，其推理速度慢且参数量大，性能落后于CNN。本文提出LE-CapsNet，一种轻量、增强且更准确的胶囊网络变体。该模型仅使用380万参数，在CIFAR-10数据集上达到76.73%的准确率，推理速度比原始CapsNet快4倍。此外，其在处理仿射变换图像时表现更鲁棒，在AffNIST数据集上实现94.3%的准确率，优于原CapsNet的90.52%。
原文摘要 · Abstract (English)
Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.3% accuracy on the AffNIST dataset (compared to CapsNet 90.52%).
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。