论文标题
HS-RESNET：卷积神经网络上的层次结构块
HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network
论文作者
论文摘要
本文介绍了名为层次结构块的代表性块，可以将其视为插入式块以升级现有的卷积神经网络，可在网络中显着提高模型性能。层次结构块包含一个单个残差块中的许多层次拆分和连接连接。我们发现多尺度功能对于众多视觉任务至关重要。此外，层次结构块非常灵活和高效，为不同的应用程序提供了巨大的潜在网络体系结构空间。在这项工作中，我们提出了一个基于层次结构块的常见主链，用于任务：图像分类，对象检测，实例分割和语义图像分割/解析。与基线相比，我们的方法对所有这些核心任务显示出显着改进。如图1所示，对于图像分类，我们的50层网络（HS-Resnet50）在ImagEnet-1K数据集上具有竞争潜伏期，达到了81.28％的TOP-1准确性。它还优于大多数最先进的模型。源代码和模型将在以下网址提供：https：//github.com/paddlepaddle/paddleclas
This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network. Hierarchical-Split Block contains many hierarchical split and concatenate connections within one single residual block. We find multi-scale features is of great importance for numerous vision tasks. Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications. In this work, we present a common backbone based on Hierarchical-Split block for tasks: image classification, object detection, instance segmentation and semantic image segmentation/parsing. Our approach shows significant improvements over all these core tasks in comparison with the baseline. As shown in Figure1, for image classification, our 50-layers network(HS-ResNet50) achieves 81.28% top-1 accuracy with competitive latency on ImageNet-1k dataset. It also outperforms most state-of-the-art models. The source code and models will be available on: https://github.com/PaddlePaddle/PaddleClas
