AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

SelfD: Self-Learning Large-Scale Driving Policies From the Web

Jimuyang Zhang, Ruizhao Zhu, Eshed Ohn-Bar

CVPR 2022 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 16 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Replace image-plane waypoint prediction and fixed perspective transform with direct BEV planningCIL planner · nuScenes SingaporeADE: 1.86 -> 1.14Improved
Add speed input to the BEV planner (ablation)BEV Planner · nuScenes SingaporeADE: 4.64 -> 1.14Improved
Add command input to a speed-conditioned BEV planner (ablation)BEV Planner · nuScenes SingaporeADE: 1.33 -> 1.14Improved
Add What If pseudo-label sampling and fine-tune on clean labeled data (ablation)SelfD · nuScenes SingaporeADE: 1.14 -> 1.00Improved
Replace What If uniform sampling with visual odometry estimates (ablation)SelfD · nuScenes SingaporeADE: 1.00 -> 1.09Hurt
Replace uniform sampling with prior-based speed and command sampling (ablation)SelfD · nuScenes SingaporeADE: 1.00 -> 1.09Hurt
Fine-tune the YouTube-pretrained policy on clean labeled data (ablation)SelfD (What If-Uniform) · WaymoADE: 2.24 -> 1.65Improved
Add YouTube self-training to the BEV plannerSelfD · nuScenes Singapore nightADE: 1.67 -> 1.28Improved
Add YouTube self-training to the BEV plannerSelfD · Waymo rainyADE: 0.70 -> 0.67No clear effect
Self-train with pseudo-labeled data from Town 1BEV Planner · CARLA Town 2Success Rate (%): 12 -> 25Improved
Add unlabeled Town 2 data to self-training (ablation)SelfD (Town 1) · CARLA Town 2Success Rate (%): 25 -> 26Improved
Repeat pseudo-labeling and fine-tuning for an additional iteration (ablation)SelfD · nuScenes SingaporeADE: 1.00 -> 1.07Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy