Filters








5 Hits in 6.2 sec

SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception [article]

Yue Meng, Yongxi Lu, Aman Raj, Samuel Sunarjo, Rui Guo, Tara Javidi, Gaurav Bansal, Dinesh Bharadia
2019 arXiv   pre-print
This paper introduces SIGNet, a novel framework that provides robust geometry perception without requiring geometrically informative labels.  ...  Unsupervised learning for geometric perception (depth, optical flow, etc.) is of great interest to autonomous systems.  ...  Semantic labels can provide rich information on 3D scene geometry.  ... 
arXiv:1812.05642v2 fatcat:s25wthtxrbdfnp3i6pzzlq5b7q

SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception

Yue Meng, Yongxi Lu, Aman Raj, Samuel Sunarjo, Rui Guo, Tara Javidi, Gaurav Bansal, Dinesh Bharadia
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper introduces SIGNet, a novel framework that provides robust geometry perception without requiring geometrically informative labels.  ...  Unsupervised learning for geometric perception (depth, optical flow, etc.) is of great interest to autonomous systems.  ...  Semantic labels can provide rich information on 3D scene geometry.  ... 
doi:10.1109/cvpr.2019.01004 dblp:conf/cvpr/MengLRSGJBB19 fatcat:c46o7rnvordzhnf62b35i3dhmy

Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation [article]

Jiaxing Yan, Hong Zhao, Penghui Bu, YuSheng Jin
2021 arXiv   pre-print
In this paper, we propose the Channel-wise Attention-based Depth Estimation Network (CADepth-Net) with two effective contributions: 1) The structure perception module employs the self-attention mechanism  ...  to capture long-range dependencies and aggregates discriminative features in channel dimensions, explicitly enhances the perception of scene structure, obtains the better scene understanding and rich  ...  Signet: 2030, 2018. 2, 3, 6, 8, 13 Semantic instance aided unsupervised 3d geometry percep- [45] Xiaolong Wang, Ross Girshick  ... 
arXiv:2112.13047v1 fatcat:z3olwqma7fhn3ahctklzh6ndza

Surround-View Cameras based Holistic Visual Perception for Automated Driving [article]

Varun Ravi Kumar
2022 arXiv   pre-print
such as geometric and semantic tasks using convolutional neural networks. 2) Using Multi-Task Learning to overcome computational bottlenecks by sharing initial convolutional layers between tasks and developing  ...  We concentrate on the following issues in order to address them: 1) Developing near-field perception algorithms with high performance and low computational complexity for various visual perception tasks  ...  [493] tries to perform unsupervised semantic segmentation by contrasting object mask proposals. Tosi et al.  ... 
arXiv:2206.05542v1 fatcat:cdpn6afpvvf7hnsvry7cqbjq3u

AIUCD2017 - Book of Abstracts

Fabio Ciotti, Gianfranco Crupi
2017
We use the resulting visual perception to improve the current model or think of a new one.  ...  of semantically similar words lie close together -are increasingly used for semantic searches in large text corpora.  ... 
doi:10.6092/unibo/amsacta/5885 fatcat:rcyjp7osmvfpvgjjg6g43fqtzi