Edge artificial intelligence hardware targets mainly inference networks that have been pretrained on massive datasets. The field of few-shot learning looks for methods that allow a network to produce high accuracy even when only a few samples of each class are available. Siamese networks can be used to tackle few-shot learning problems and are unique because they do not require retraining on the new samples of the new classes. Therefore they are suitable for edge hardware accelerators which often do not include on-chip training capabilities. This work describes improvements to a baseline Siamese network and benchmarking of the improved network on edge platforms. The modifications to the baseline network included adding multi-resolution kernels, a hybrid training process as well a different embedding similarity computation method. This network shows an average accuracy improvement of up to 22% across 4 datasets in a 5-way, 1-shot classification task. Benchmarking results using three edge computing platforms (NVIDIA Jetson Nano, Coral Edge TPU and a custom convolutional neural network accelerator) show that a Siamese classifier can run on these devices at reasonable frame rates for real-time performance, between 3 frames per second (FPS) on Jetson Nano and 60 FPS on the Edge TPU. By increasing the weight sparsity during training, the inference time of a network with 25% weight sparsity increases by 10 FPS but with only 1% drop in accuracy.

中文翻译：

---

用于边缘嵌入式设备上的小样本学习的 Siamese 网络

边缘人工智能硬件主要针对已在海量数据集上进行预训练的推理网络。小样本学习领域寻找方法，即使每个类只有几个样本可用，也能让网络产生高精度。Siamese 网络可用于解决小样本学习问题，并且是独一无二的，因为它们不需要对新类的新样本进行再训练。因此，它们适用于通常不包括片上训练功能的边缘硬件加速器。这项工作描述了对基线 Siamese 网络的改进以及对边缘平台上改进网络的基准测试。对基线网络的修改包括添加多分辨率内核、混合训练过程以及不同的嵌入相似度计算方法。在 5 路 1 次分类任务中，该网络在 4 个数据集上的平均准确率提高了 22%。使用三个边缘计算平台（NVIDIA Jetson Nano、Coral Edge TPU 和自定义卷积神经网络加速器）的基准测试结果表明，Siamese 分类器可以在这些设备上以合理的帧速率运行，以实现实时性能，每秒 3 帧 (FPS) ) Jetson Nano 和 Edge TPU 上的 60 FPS。通过在训练期间增加权重稀疏度，权重稀疏度为 25% 的网络的推理时间增加了 10 FPS，但准确率仅下降了 1%。Coral Edge TPU 和自定义卷积神经网络加速器）表明，连体分类器可以在这些设备上以合理的帧速率运行，以实现实时性能，Jetson Nano 上的每秒 3 帧 (FPS) 和 Edge TPU 上的 60 FPS。通过在训练期间增加权重稀疏度，权重稀疏度为 25% 的网络的推理时间增加了 10 FPS，但准确率仅下降了 1%。Coral Edge TPU 和自定义卷积神经网络加速器）表明，连体分类器可以在这些设备上以合理的帧速率运行，以实现实时性能，Jetson Nano 上的每秒 3 帧 (FPS) 和 Edge TPU 上的 60 FPS。通过在训练期间增加权重稀疏度，权重稀疏度为 25% 的网络的推理时间增加了 10 FPS，但准确率仅下降了 1%。