Sign In
insight - Multi-task Learning in Autonomous Driving
Real-time Multi-task Learning for Autonomous Driving with Task-adaptive Attention Generator
The author presents a real-time multi-task learning approach for autonomous driving, focusing on 3D object detection, semantic segmentation, and dense depth estimation. The proposed model addresses the negative transfer problem in multi-task learning while ensuring computational efficiency.
PanDepth: Joint Panoptic Segmentation and Depth Completion Study
提案されたPanDepthモデルは、RGB画像と疎な深度マップを使用してパノプティックセグメンテーションと深度補完を行う多目的モデルであり、複数のコンピュータビジョンタスクを解決し、高い精度を維持します。