English

An attention-driven hierarchical multi-scale representation for visual recognition

Computer Vision and Pattern Recognition 2021-10-26 v1 Artificial Intelligence Machine Learning

Abstract

Convolutional Neural Networks (CNNs) have revolutionized the understanding of visual content. This is mainly due to their ability to break down an image into smaller pieces, extract multi-scale localized features and compose them to construct highly expressive representations for decision making. However, the convolution operation is unable to capture long-range dependencies such as arbitrary relations between pixels since it operates on a fixed-size window. Therefore, it may not be suitable for discriminating subtle changes (e.g. fine-grained visual recognition). To this end, our proposed method captures the high-level long-range dependencies by exploring Graph Convolutional Networks (GCNs), which aggregate information by establishing relationships among multi-scale hierarchical regions. These regions consist of smaller (closer look) to larger (far look), and the dependency between regions is modeled by an innovative attention-driven message propagation, guided by the graph structure to emphasize the neighborhoods of a given region. Our approach is simple yet extremely effective in solving both the fine-grained and generic visual classification problems. It outperforms the state-of-the-arts with a significant margin on three and is very competitive on other two datasets.

Keywords

Cite

@article{arxiv.2110.12178,
  title  = {An attention-driven hierarchical multi-scale representation for visual recognition},
  author = {Zachary Wharton and Ardhendu Behera and Asish Bera},
  journal= {arXiv preprint arXiv:2110.12178},
  year   = {2021}
}

Comments

Accepted in the 32nd British Machine Vision Conference (BMVC) 2021

R2 v1 2026-06-24T07:07:30.347Z