5 citations · 12 across the 11 of their papers we have counts for
11 papers
InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams
Shuai Yuan, Yantai Yang, Xiaotian Yang +4
The grand vision of enabling persistent, large-scale 3D visual geometry understanding is shackled by the irreconcilable demands of scalability and long-term stability. While offlin…
Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classification
Kelsey Lieberman, Swarna Kamlam Ravindran, Shuai Yuan +1
Although binary classification is a well-studied problem, training reliable classifiers under severe class imbalance remains a challenge. Recent techniques mitigate the ill effects…
UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model
Shuai Yuan, Lei Luo, Zhuo Hui +4
Traditional unsupervised optical flow methods are vulnerable to occlusions and motion boundaries due to lack of object-level information. Therefore, we propose UnSAMFlow, an unsupe…
Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functions
Kelsey Lieberman, Shuai Yuan, Swarna Kamlam Ravindran +1
Although binary classification is a well-studied problem in computer vision, training reliable classifiers under severe class imbalance remains a challenging problem. Recent work h…
UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation
Shuai Yuan, Carlo Tomasi
Both optical flow and stereo disparities are image matches and can therefore benefit from joint training. Depth and 3D motion provide geometric rather than photometric information…
Mitigating Test-Time Bias for Fair Image Retrieval
Fanjie Kong, Shuai Yuan, Weituo Hao +1
We address the challenge of generating fair and unbiased image retrieval results given neutral textual queries (with no explicit gender or race connotations), while maintaining the…
SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving
Shuai Yuan, Shuzhi Yu, Hannah Kim +1
Unsupervised optical flow estimation is especially hard near occlusions and motion boundaries and in low-texture regions. We show that additional information such as semantics and…
Unsupervised Flow Refinement near Motion Boundaries
Shuzhi Yu, Hannah Halin Kim, Shuai Yuan +1
Unsupervised optical flow estimators based on deep learning have attracted increasing attention due to the cost and difficulty of annotating for ground truth. Although performance…
Cross-Attention Transformer for Video Interpolation
Hannah Halin Kim, Shuzhi Yu, Shuai Yuan +1
We propose TAIN (Transformers and Attention for video INterpolation), a residual neural network for video interpolation, which aims to interpolate an intermediate frame given two c…
Optical Flow Training under Limited Label Budget via Active Learning
Shuai Yuan, Xian Sun, Hannah Kim +2
Supervised training of optical flow predictors generally yields better accuracy than unsupervised training. However, the improved performance comes at an often high annotation cost…
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach
Xiang Wang, Shuai Yuan, Chenwei Wu +1
Choosing the right parameters for optimization algorithms is often the key to their success in practice. Solving this problem using a learning-to-learn approach -- using meta-gradi…