← Search

Tsung-Lin Tsou

2 accepted papers

2024

WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection

ICRA 2024poster

In the field of domain adaptation (DA) on 3D object detection, most of the work is dedicated to unsupervised domain adaptation (UDA). Yet, without any target annotations, the performance gap between the UDA approaches and the fully-supervised approach is still noticeable, which is impractical for re…

Cited by 0SourcecodeScholar
2021

S3: Learnable Sparse Signal Superdensity for Guided Depth Estimation

CVPR 2021poster

Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been leveraged as guidance for enhancing dense depth estimation, the improvement is limited due to its low density and imbalanc…

Cited by 22PDFScholar