ResNeSt: Split-Attention Networks

作者：Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Haibin Lin, Zhi Zhang, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander J. Smola · 发表于：2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 年份：2022 · DOI：10.1109/cvprw56347.2022.00309 · 被引用次数：1320 · 研究领域：Advanced Neural Network Applications、Domain Adaptation and Few-Shot Learning、Multimodal Machine Learning Applications

The ability to learn richer network representations generally boosts the performance of deep learning models. To improve representation-learning in convolutional neural networks, we present a multi-branch architecture, which applies channel-wise attention across different network branches to leverage the complementary strengths of both feature-map attention and multi-path representation. Our proposed Split-Attention module provides a simple and modular computation block that can serve as a drop-in replacement for the popular residual block, while producing more diverse representations via cross-feature interactions. Adding a Split-Attention module into the architecture design space of RegNet-Y and FBNetV2 directly improves the performance of the resulting network. Replacing residual blocks with our Split-Attention module, we further design a new variant of the ResNet model, named ResNeSt, which outperforms EfficientNet in terms of the accuracy/latency trade-off.