论文标题
重新思考具有极低记忆足迹的边缘设备的美国手语预测中的概括
Rethinking Generalization in American Sign Language Prediction for Edge Devices with Extremely Low Memory Footprint
论文作者
论文摘要
由于过去几年技术计算的繁荣，全世界在人工智能系统中解决了各种现实世界中的问题的巨大进步。但是，这些模型无处不在接受的主要障碍是它们的巨大计算复杂性和记忆足迹。因此，在极低的资源推理端点上部署需要有效的架构和培训技术。本文提出了一种用于在Arm Cortex-M7微控制器上使用American手语的字母的架构，仅具有496 kb的Framebuffer RAM。利用参数量化是一种常见技术，可能导致测试准确性下降。本文提出，将插值用作其他技术之间的增强作用，作为减少此下降的有效方法，这也有助于模型可以很好地推广到以前看不见的嘈杂数据。提出的模型约为185 kb，定量后，推理速度为每秒20帧。
Due to the boom in technical compute in the last few years, the world has seen massive advances in artificially intelligent systems solving diverse real-world problems. But a major roadblock in the ubiquitous acceptance of these models is their enormous computational complexity and memory footprint. Hence efficient architectures and training techniques are required for deployment on extremely low resource inference endpoints. This paper proposes an architecture for detection of alphabets in American Sign Language on an ARM Cortex-M7 microcontroller having just 496 KB of framebuffer RAM. Leveraging parameter quantization is a common technique that might cause varying drops in test accuracy. This paper proposes using interpolation as augmentation amongst other techniques as an efficient method of reducing this drop, which also helps the model generalize well to previously unseen noisy data. The proposed model is about 185 KB post-quantization and inference speed is 20 frames per second.
