Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models.
Modern LiDAR-SLAM (L-SLAM) systems have shown excellent results in large-scale, real-world scenarios.
We present a robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass.
To minimize the detrimental effect of extrinsic perturbation, we propagate an uncertainty prior on each point of input point clouds, and use this information to boost an approach for 3D geometric tasks.
no code implementations • 16 Apr 2020 • Tianyu Liu, Qinghai Liao, Lu Gan, Fulong Ma, Jie Cheng, Xupeng Xie, Zhe Wang, Yingbing Chen, Yilong Zhu, Shuyang Zhang, Zhengyong Chen, Yang Liu, Meng Xie, Yang Yu, Zitong Guo, Guang Li, Peidong Yuan, Dong Han, Yuying Chen, Haoyang Ye, Jianhao Jiao, Peng Yun, Zhenhua Xu, Hengli Wang, Huaiyang Huang, Sukai Wang, Peide Cai, Yuxiang Sun, Yandong Liu, Lujia Wang, Ming Liu
Moreover, many countries have imposed tough lockdown measures to reduce the virus transmission (e. g., retail, catering) during the pandemic, which causes inconveniences for human daily life.
End-to-end visual-based imitation learning has been widely applied in autonomous driving.
Inspired by the recent use of focal loss in image-based object detection, we extend this hard-mining improvement of binary cross entropy to point-cloud-based object detection and conduct experiments to show its performance based on two different 3D detectors: 3D-FCN and VoxelNet.
We take the spherical image, which is transformed from the 3D LiDAR point clouds, as input of the convolutional neural networks (CNNs) to predict the point-wise semantic map.
In this paper, we deal with the reality gap from a novel perspective, targeting transferring Deep Reinforcement Learning (DRL) policies learned in simulated environments to the real-world domain for visual control tasks.