Fine-Grained Dynamic Head for Object Detection

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.

Authors

• Lin Song
• Yanwei Li
• Zhengkai Jiang Tencent Youtu Lab
• Zeming Li MEGVII Technology
• Hongbin Sun
• Jian Sun Xi'an Jiaotong University Pazhou Laboratory (Huangpu), China Peng Cheng Laboratory, China
• Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University

Keywords

No keywords are indexed for this paper.