Res2Net: A New Multi-Scale Backbone Architecture

Nankai University · University of California, Merced · +1 more institution

PubMed
Indexed inarxivcrossrefpubmed

Abstract

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be…

Citation impact

3,314
total citations
FWCI
116.66
Percentile
100%
References
115
Citations per year

Authors

6

Topics & keywords

Keywords
  • Computer science
  • Block (permutation group theory)
  • Artificial intelligence
  • Residual
  • Backbone network
  • Convolutional neural network
  • Object detection
  • Pattern recognition (psychology)
UN Sustainable Development Goals
  • Sustainable cities and communities
No related works found for this paper.

Funding