234 citations · 717 across the 50 of their papers we have counts for
10 papers · 1 filter
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
Lingdong Kong, Yaru Niu, Shaoyuan Xie +39
Accurate depth estimation under out-of-distribution (OoD) scenarios, such as adverse weather conditions, sensor failure, and noise contamination, is desirable for safety-critical a…
CLiNet: Joint Detection of Road Network Centerlines in 2D and 3D
David Paz, Srinidhi Kalgundi Srinivas, Yunchao Yao +1
This work introduces a new approach for joint detection of centerlines based on image data by localizing the features jointly in 2D and 3D. In contrast to existing work that focuse…
MOMA:Distill from Self-Supervised Teachers
Yuchong Yao, Nandakishor Desai, Marimuthu Palaniswami
Contrastive Learning and Masked Image Modelling have demonstrated exceptional performance on self-supervised representation learning, where Momentum Contrast (i.e., MoCo) and Maske…
Exploring Vision Transformers as Diffusion Learners
He Cao, Jianan Wang, Tianhe Ren +4
Score-based diffusion models have captured widespread attention and funded fast progress of recent vision generative tasks. In this paper, we focus on diffusion model backbone whic…
3D Point Cloud Pre-training with Knowledge Distillation from 2D Images
Yuan Yao, Yuanhan Zhang, Zhenfei Yin +3
The recent success of pre-trained 2D vision models is mostly attributable to learning from large-scale datasets. However, compared with 2D image datasets, the current pre-training…
Masked Contrastive Representation Learning
Yuchong Yao, Nandakishor Desai, Marimuthu Palaniswami
Masked image modelling (e.g., Masked AutoEncoder) and contrastive learning (e.g., Momentum Contrast) have shown impressive performance on unsupervised visual representation learnin…