activity
20222024
most citedOn the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning

6 citations · 8 across the 5 of their papers we have counts for

collaborators

5 papers

eess.IV20241 cited

Learning 3D Gaussians for Extremely Sparse-View Cone-Beam CT Reconstruction

Yiqun Lin, Hualiang Wang, Jixiang Chen +1

Cone-Beam Computed Tomography (CBCT) is an indispensable technique in medical imaging, yet the associated radiation exposure raises concerns in clinical practice. To mitigate these…

eess.IV20241 cited

C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction

Yiqun Lin, Jiewen Yang, Hualiang Wang +3

Cone beam computed tomography (CBCT) is an important imaging technology widely used in medical scenarios, such as diagnosis and preoperative planning. Using fewer projection views…

cs.CV2023

Uniformly Distributed Category Prototype-Guided Vision-Language Framework for Long-Tail Recognition

Siming Fu, Xiaoxuan He, Xinpeng Ding +2

Recently, large-scale pre-trained vision-language models have presented benefits for alleviating class imbalance in long-tailed recognition. However, the long-tailed data distribut…

cs.CV20236 cited

On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning

Jianhong Bai, Zuozhu Liu, Hualiang Wang +4

Though Self-supervised learning (SSL) has been widely studied as a promising technique for representation learning, it doesn't generalize well on long-tailed datasets due to the ma…

cs.CV2022

Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning

Hualiang Wang, Siming Fu, Xiaoxuan He +3

Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little at…