Local Relation Networks for Image Recognition

Han Hu, Zheng Zhang, Zhenda Xie, Stephen Lin; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 3464-3473

Abstract


The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process that applies fixed filters which are inefficient at modeling visual elements with varying spatial distributions. This paper presents a new image feature extractor, called the local relation layer, that adaptively determines aggregation weights based on the compositional relationship of local pixel pairs. With this relational approach, it can composite visual elements into higher-level entities in a more efficient manner that benefits semantic inference. A network built with local relation layers, called the Local Relation Network (LR-Net), is found to provide greater modeling capacity than its counterpart built with regular convolution on large-scale recognition tasks such as ImageNet classification.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Hu_2019_ICCV,
author = {Hu, Han and Zhang, Zheng and Xie, Zhenda and Lin, Stephen},
title = {Local Relation Networks for Image Recognition},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}