论文标题
高斯公羊：通过随机视网膜风格的瞥见和增强学习的轻量级图像分类
Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement Learning
论文作者
论文摘要
先前关于图像分类的研究主要集中在网络的性能上，而不是实时操作或模型压缩。我们提出了一个高斯深度复发视觉注意模型（GDRAM） - 用于大规模图像分类的基于增强学习的轻巧的深神经网络，该网络的表现优于常规CNN（卷积神经网络），该网络（卷积神经网络）使用整个图像作为输入。受到生物视觉识别过程的高度启发，我们的模型模仿了带有高斯分布的视网膜的随机位置。我们评估了大型混乱的MNIST，大CIFAR-10和大型CIFAR-100数据集的模型，这些数据集的宽度和高度都在128中。
Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM)- a reinforcement learning based lightweight deep neural network for large scale image classification that outperforms the conventional CNN (Convolutional Neural Network) which uses the entire image as input. Highly inspired by the biological visual recognition process, our model mimics the stochastic location of the retina with Gaussian distribution. We evaluate the model on Large cluttered MNIST, Large CIFAR-10 and Large CIFAR-100 datasets which are resized to 128 in both width and height.
