paper-with-me

홈 › Papers

Hierarchical Recurrent Attention Networks for Structured Online Maps

2020-12-22 · CVPR 2018 6 · Namdar Homayounfar, Wei-Chiu Ma, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun

In this paper, we tackle the problem of online road network extraction from sparse 3D point clouds. Our method is inspired by how an annotator builds a lane graph, by first identifying how many lanes there are and then drawing each one in turn. We develop a hierarchical recurrent network that attends to initial regions of a lane boundary and traces them out completely by outputting a structured polyline. We also propose a novel differentiable loss function that measures the deviation of the edges of the ground truth polylines and their predictions. This is more suitable than distances on vertices, as there exists many ways to draw equivalent polylines. We demonstrate the effectiveness of our method on a 90 km stretch of highway, and show that we can recover the right topology 92\% of the time.

📄 PDF Abstract BibTeX arXiv:2012.12314

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The Importance of Being Recurrent for Modeling Hierarchical Structure

2018-03-09 · EMNLP 2018 10 · Ke Tran, Arianna Bisazza, Christof Monz

Recent work has shown that recurrent neural networks (RNNs) can implicitly capture and exploit hierarchical information when trained to solve common natural language processing tasks such as language modeling (Linzen et …

Language ModelingLanguage ModellingMachine TranslationTranslation

Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding

2017-10-01 · ICCV 2017 10 · Zhenxing Niu, Mo Zhou, Le Wang, Xinbo Gao 외

We address the problem of dense visual-semantic embedding that maps not only full sentences and whole images but also phrases within sentences and salient regions within images into a multimodal embedding space. As a res…

Sentence

Parallel Recursive LSTM

2026-05-16 · Tristan Gaudreault, Yongyi Mao arxiv

Transformers have become the dominant architecture for sequence modeling by using self-attention to enable expressive and highly parallel processing. However, the resulting quadratic time and memory costs limit efficienc…

Hierarchical Road Topology Learning for Urban Map-less Driving

2021-03-31 · Li Zhang, Faezeh Tafazzoli, Gunther Krehl, Runsheng Xu 외

The majority of current approaches in autonomous driving rely on High-Definition (HD) maps which detail the road geometry and surrounding area. Yet, this reliance is one of the obstacles to mass deployment of autonomous …

Autonomous DrivingAutonomous Vehicles

Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation

2021-10-08 · Chao Huang, Jiahui Chen, Lianghao Xia, Yong Xu 외

Session-based recommendation plays a central role in a wide spectrum of online applications, ranging from e-commerce to online advertising services. However, the majority of existing session-based recommendation techniqu…

Graph Neural NetworkMulti-Task LearningRelationSession-Based Recommendations