论文标题
Resnest：分裂注意网络
ResNeSt: Split-Attention Networks
论文作者
论文摘要
众所周知，特征的注意力和多路径表示对于视觉识别很重要。在本文中，我们提出了一个模块化的体系结构，该体系结构在不同的网络分支上应用了渠道的关注，以利用其成功在捕获交叉互动和学习各种表示形式方面的成功。我们的设计产生了一个简单而统一的计算块，可以仅使用几个变量进行参数化。我们的模型（名为Resnest）在图像分类上的准确性和延迟权衡方面优于效率网络。此外，Resnest在几个用作骨干的公共基准上取得了卓越的转移学习结果，并已被可可LVIS挑战的获胜参赛作品所采用。完整系统和验证模型的源代码可公开使用。
It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.
