用RNN处理图像像素序列，适合资源受限的嵌入式设备。
Recurrent Neural Networks for Still Images
- 将图像像素视为序列，用改进的RNN处理二维数据
- 在COCO和CIFAR100上小模型表现优于传统方法
- 新设计的双向RNN更省内存，适合边缘计算
本文探索了将循环神经网络（RNN）应用于静态图像的可能性。通常，卷积神经网络（CNN）是处理此类数据的主流方法，而近期变换器也日益流行，但往往需要大型模型。与这些方法不同，RNN通常用于时序数据处理，而非单张图像。本文认为，通过将像素视为序列，RNN可有效处理静态图像，尤其适用于资源受限的嵌入式系统中的紧凑模型。为此，我们提出一种专为二维输入（如图像）设计的新颖RNN结构，以及一种比传统实现更节省内存的双向RNN（BiRNN）变体。研究中，我们在以Conv2D层为主、末端或近末端加入RNN层的卷积循环神经网络（CRNN）上进行了测试。在COCO和CIFAR100数据集上的实验表明，该方法在小型网络中表现更优。
原文摘要 · Abstract (English)
In this paper, we explore the application of Recurrent Neural Network (RNN) for still images. Typically, Convolutional Neural Networks (CNNs) are the prevalent method applied for this type of data, and more recently, transformers have gained popularity, although they often require large models. Unlike these methods, RNNs are generally associated with processing sequences over time rather than single images. We argue that RNNs can effectively handle still images by interpreting the pixels as a sequence. This approach could be particularly advantageous for compact models designed for embedded systems, where resources are limited. Additionally, we introduce a novel RNN design tailored for two-dimensional inputs, such as images, and a custom version of BiDirectional RNN (BiRNN) that is more memory-efficient than traditional implementations. In our research, we have tested these layers in Convolutional Recurrent Neural Networks (CRNNs), predominantly composed of Conv2D layers, with RNN layers at or close to the end. Experiments on the COCO and CIFAR100 datasets show better results, particularly for small networks.
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。