Timezone: »

Fine-Grained Dynamic Head for Object Detection
Lin Song · Yanwei Li · Zhengkai Jiang · Zeming Li · Hongbin Sun · Jian Sun · Nanning Zheng

Tue Dec 08 09:00 PM -- 11:00 PM (PST) @ Poster Session 2 #743

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.

Author Information

Lin Song (Xi'an Jiaotong University)
Yanwei Li (The Chinese University of Hong Kong)
Zhengkai Jiang (Institute of Automation,Chinese Academy of Sciences)
Zeming Li (Megvii(Face++) Inc)
Hongbin Sun (Xi'an Jiaotong University)
Jian Sun (Megvii, Face++)
Nanning Zheng (Xi'an Jiaotong University)

More from the Same Authors