Fine-Grained Dynamic Head for Object Detection

Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Hongbin Sun, Jian Sun, Nanning Zheng

Abstract

The Feature Pyramid Network (FPN) presents a remarkable approach to alleviate the scale variance in object representation by performing instance-level assignments. Nevertheless, this strategy ignores the distinct characteristics of different sub-regions in an instance. To this end, we propose a fine-grained dynamic head to conditionally select a pixel-level combination of FPN features from different scales for each instance, which further releases the ability of multi-scale feature representation. Moreover, we design a spatial gate with the new activation function to reduce computational complexity dramatically through spatially sparse convolutions. Extensive experiments demonstrate the effectiveness and efficiency of the proposed method on several state-of-the-art detection benchmarks. Code is available at https://github.com/StevenGrove/DynamicHead.
BibTeX
@inproceedings{song2020fine,
  author = {Lin Song and Yanwei Li and Zhengkai Jiang and Zeming Li and Hongbin Sun and Jian Sun and Nanning Zheng},
  title = {{Fine-Grained Dynamic Head for Object Detection}},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2020},
  url = {https://openreview.net/forum?id=9v_1piEk6z7},
}

Loading related content...

Figure