no code implementations • 20 May 2024 • Wentao Wang, Xi Xiao, Mingjie Liu, Qing Tian, Xuanyao Huang, Qizhen Lan, Swalpa Kumar Roy, Tianyang Wang
MDT-AF incorporates an attention-based feature filtering mechanism into the patch embedding blocks and employs a coarse-to-fine process to mitigate the impact of low signal-to-noise ratio.
no code implementations • 7 Mar 2023 • Lijing Zhu, Qizhen Lan, Alvaro Velasquez, Houbing Song, Acharya Kamal, Qing Tian, Shuteng Niu
Our method effectively captures the sentiment representation of HOIs by integrating both spatial and semantic knowledge.
Computational Efficiency Human-Object Interaction Detection +1
no code implementations • 7 Mar 2023 • Qizhen Lan, Qing Tian
In this paper, we propose a novel approach for knowledge distillation in object detection, named Gradient-guided Knowledge Distillation (GKD).
no code implementations • 26 Jan 2022 • Qizhen Lan, Qing Tian
In this paper, we propose Adaptive Instance Distillation (AID) to selectively impart teacher's knowledge to the student to improve the performance of knowledge distillation.