2 papers
cs.CV2020
Fixed-size Objects Encoding for Visual Relationship Detection
Hengyue Pan, Xin Niu, Rongchun Li +2
In this paper, we propose a fixed-size object encoding method (FOE-VRD) to improve performance of visual relationship detection tasks. Comparing with previous methods, FOE-VRD has…
cs.LG2018
DropFilter: A Novel Regularization Method for Learning Convolutional Neural Networks
Hengyue Pan, Hui Jiang, Xin Niu +1
The past few years have witnessed the fast development of different regularization methods for deep learning models such as fully-connected deep neural networks (DNNs) and Convolut…