CARLANE: A Lane Detection Benchmark for Unsupervised Domain Adaptation from Simulation to multiple Real-World Domains
Nov 28, 2022
Speakers
Julian Gebele
Speaker · 0 followers
Bonifaz Stuhr
Speaker · 0 followers
Johann Haselberger
Speaker · 0 followers
About
Unsupervised Domain Adaptation demonstrates great potential to mitigate domain shifts by transferring models from labeled source domains to unlabeled target domains. While Unsupervised Domain Adaptation has been applied to a wide variety of complex vision tasks, only few works focus on lane detection for autonomous driving. This can be attributed to the lack of publicly available datasets. To facilitate research in these directions, we propose CARLANE, a 3-way sim-to-real domain adaptation benchmark for 2D lane detection. CARLANE encompasses the single-target datasets MoLane and TuLane and the multi-target dataset MuLane. These datasets are built from three different domains, which cover diverse scenes and contain a total of 163K unique images, 118K of which are annotated. In addition we evaluate and report systematic baselines, including our own method, which builds upon Prototypical Cross-domain Self-supervised Learning. We find that false positive and false negative rates of the evaluated domain adaptation methods are high compared to those of fully supervised baselines. This affirms the need for benchmarks such as CARLANE to further strengthen research in Unsupervised Domain Adaptation for lane detection. CARLANE, all evaluated models and the corresponding implementations are publicly available at https://carlanebenchmark.github.io.Unsupervised Domain Adaptation demonstrates great potential to mitigate domain shifts by transferring models from labeled source domains to unlabeled target domains. While Unsupervised Domain Adaptation has been applied to a wide variety of complex vision tasks, only few works focus on lane detection for autonomous driving. This can be attributed to the lack of publicly available datasets. To facilitate research in these directions, we propose CARLANE, a 3-way sim-to-real domain adaptation benc…
Organizer
NeurIPS 2022
Account · 956 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Choreographer: Learning and Adapting Skills in Imagination
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief
Watch later
Kaiyang Guo, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE
Watch later
Yewen Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Posterior Matching for Arbitrary Conditioning
Watch later
Ryan Strauss, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Offline RL with Closed-Form Policy Improvement Operators
Watch later
Jiachen Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning to Share in Multi-Agent Reinforcement Learning
Watch later
Yuxuan Yi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%