Publications (11)
Learning with Free Object Segments for Long-Tailed Instance Segmentation
Cheng Zhang, Tai-Yu Pan, Tianle Chen +3
One fundamental challenge in building an instance segmentation model for a large number of classes in complex scenes is the lack of training examples, especially for rare objects.…
Pre-Training LiDAR-Based 3D Object Detectors Through Colorization
Tai-Yu Pan, Chenyang Ma, Tianle Chen +7
Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts of labeled data to train. In this work, we in…
Static Segmentation by Tracking: A Label-Efficient Approach for Fine-Grained Specimen Image Segmentation
Zhenyang Feng, Zihe Wang, Jianyang Gu +22
We study image segmentation in the biological domain, particularly trait segmentation from specimen images (e.g., butterfly wing stripes, beetle elytra). This fine-grained task is…
MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
Cheng Zhang, Tai-Yu Pan, Yandong Li +5
Many objects do not appear frequently enough in complex scenes (e.g., certain handbags in living rooms) for training an accurate object detector, but are often found frequently by…
When the City Teaches the Car: Label-Free 3D Perception from Infrastructure
Zhen Xu, Jinsu Yoo, Cristian Bautista +7
Building robust 3D perception for self-driving still relies heavily on large-scale data collection and manual annotation, yet this paradigm becomes impractical as deployment expand…
Leveraging Sparse LiDAR for RAFT-Stereo: A Depth Pre-Fill Perspective
Jinsu Yoo, Sooyoung Jeon, Zanming Huang +2
We investigate LiDAR guidance within the RAFT-Stereo framework, aiming to improve stereo matching accuracy by injecting precise LiDAR depth into the initial disparity map. We find…