当前位置 >>成果展示 >>论文

Monocular Viewpoints Estimation for Generic Objects in the Wild.(IEEE Access 2019)时间: 2019-07-31 点击: 272 次



Authors:Zhigang Li;Yuwang Wang;Xiangyang Ji.


Abstract:
Although classification-based approaches achieved remarkable performance in viewpoints estimation, they still have limitations and face the challenging viewpoints ambiguity problem. In this paper, we analyze this problem and give solutions: 1) we propose Viewpoint Discernibility Matrix (VDM) loss, which is a more suitable loss than the one-hot cross-entropy loss by tolerating the sub-optimal predictions and penalizing the wrong predictions on ambiguous viewpoints; and 2) we propose Auxiliary Hierarchical Viewpoints Supervision (AHVS) method, which is able to restrain the network to pay closer attention to the features of ambiguous viewpoints. Training with VDM loss and AHVS, the model is endowed with strong representation ability to achieve significant improvements on viewpoints estimation. Extensive experiments are conducted and show the superiority of our approach. On the large Pascal3D+ dataset, we achieve the state-of-the-art results among all commonly used metrics.
Published in: IEEE Access ( Volume: 7 )
Page(s): 94321 - 94331
Date of Publication: 17 June 2019
Electronic ISSN: 2169-3536
INSPEC Accession Number: 18843717
Publisher: IEEE
Funding Agency:




上一篇:High-Performance FPGA-Based CNN Accelerator With Block-Floating-Point Arithmetic.( IEEE T VLSI SYST 2019) 下一篇:3D Fourier Ptychographic Microscopy Based on the Beam Propagation Method and Time-Reversal Scheme.(IEEE Access 2019) 返回列表

用户登录

用户注册