← Search

Yi-Syuan Liou

2 accepted papers

2023

Revisiting Depth-guided Methods for Monocular 3D Object Detection by Hierarchical Balanced Depth

CoRL 2023poster

Monocular 3D object detection has seen significant advancements with the incorporation of depth information. However, there remains a considerable performance gap compared to LiDAR-based methods, largely due to inaccurate depth estimation. We argue that this issue stems from the commonly used pixel-…

Cited by 1SourceScholar
2022

D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation

ECCV 2022poster

"In the field of domain adaptation, a trade-off exists between the model performance and the number of target domain annotations. Active learning, maximizing model performance with few informative labeled data, comes in handy for such a scenario. In this work, we present D2ADA, a general active doma…