论文标题
Imagesig：超轻质图像识别的签名变换
ImageSig: A signature transform for ultra-lightweight image recognition
论文作者
论文摘要
本文介绍了一种新的轻巧方法，以识别图像识别。 Imagesig基于计算标志，不需要卷积结构或基于注意力的编码器。它对作者的实现是惊人的：a）超过许多最先进方法的64 x 64 RGB图像的准确性，同时b）需要减少拖鞋，功率和内存足迹的数量级。预验证的模型的大小可以小至44.2 kb。 Imagesig在硬件（例如Raspberry Pi和Jetson-Nano）上显示了前所未有的性能。 Imagesig将图像视为带有多个通道的流。这些流是通过空间方向参数化的。我们为签名和粗糙路径理论的功能做出了贡献，以在时间流以外的静态图像上进行类似流的数据和视觉任务。对于很少的参数和小尺寸模型，关键优势在于，可以将其中许多“检测器”组装在同一芯片上。此外，可以执行一次功能采集并在不同任务的不同模型之间共享 - 进一步加速了该过程。这有助于能源效率和边缘嵌入的AI的进步。
This paper introduces a new lightweight method for image recognition. ImageSig is based on computing signatures and does not require a convolutional structure or an attention-based encoder. It is striking to the authors that it achieves: a) an accuracy for 64 X 64 RGB images that exceeds many of the state-of-the-art methods and simultaneously b) requires orders of magnitude less FLOPS, power and memory footprint. The pretrained model can be as small as 44.2 KB in size. ImageSig shows unprecedented performance on hardware such as Raspberry Pi and Jetson-nano. ImageSig treats images as streams with multiple channels. These streams are parameterized by spatial directions. We contribute to the functionality of signature and rough path theory to stream-like data and vision tasks on static images beyond temporal streams. With very few parameters and small size models, the key advantage is that one could have many of these "detectors" assembled on the same chip; moreover, the feature acquisition can be performed once and shared between different models of different tasks - further accelerating the process. This contributes to energy efficiency and the advancements of embedded AI at the edge.
