English

DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection

Computer Vision and Pattern Recognition 2021-03-26 v2

Abstract

Although object detection has reached a milestone thanks to the great success of deep learning, the scale variation is still the key challenge. Integrating multi-level features is presented to alleviate the problems, like the classic Feature Pyramid Network (FPN) and its improvements. However, the specifically designed feature integration modules of these methods may not have the optimal architecture for feature fusion. Moreover, these models have fixed architectures and data flow paths, when fed with various samples. They cannot adjust and be compatible with each kind of data. To overcome the above limitations, we propose a Dynamic Sample-Individualized Connector (DSIC) for multi-scale object detection. It dynamically adjusts network connections to fit different samples. In particular, DSIC consists of two components: Intra-scale Selection Gate (ISG) and Cross-scale Selection Gate (CSG). ISG adaptively extracts multi-level features from backbone as the input of feature integration. CSG automatically activate informative data flow paths based on the multi-level features. Furthermore, these two components are both plug-and-play and can be embedded in any backbone. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts.

Keywords

Cite

@article{arxiv.2011.07774,
  title  = {DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection},
  author = {Zekun Li and Yufan Liu and Bing Li and Weiming Hu},
  journal= {arXiv preprint arXiv:2011.07774},
  year   = {2021}
}
R2 v1 2026-06-23T20:16:01.901Z