Search Results for author:
Found 9 papers, 4 papers with code
Towards Demystifying the Generalization Behaviors When Neural Collapse Emerges
While there have been extensive studies on optimization characteristics showing the global optimality of neural collapse, little research has been done on the generalization behaviors during the occurrence of NC.
AUC-Oriented Domain Adaptation: From Theory to Algorithm
We propose a new result that not only addresses the interdependency issue but also brings a much sharper bound with weaker assumptions about the loss function.
A Study of Neural Collapse Phenomenon: Grassmannian Frame, Symmetry and Generalization
Out of curiosity about the symmetry of Grassmannian Frame, we conduct experiments to explore if models with different Grassmannian Frames have different performance.
Building Bridge Across the Time: Disruption and Restoration of Murals In the Wild
Finally, experimental results support the effectiveness of the proposed framework in terms of both mural synthesis and restoration.
Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective
Positive-Unlabeled (PU) learning tries to learn binary classifiers from a few labeled positive examples with many unlabeled ones.
Exploring the Algorithm-Dependent Generalization of AUPRC Optimization with List Stability
Stochastic optimization of the Area Under the Precision-Recall Curve (AUPRC) is a crucial problem for machine learning.
When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking
To leverage high performance under low FPRs, we consider an alternative metric for multipartite ranking evaluating the True Positive Rate (TPR) at a given FPR, denoted as TPR@FPR.
When False Positive is Intolerant: End-to-End Optimization with Low FPR for Multipartite Ranking
To leverage high performance under low FPRs, we consider an alternative metric for multipartite ranking evaluating the True Positive Rate (TPR) at a given FPR, denoted as TPR@FPR.
Seeking the Shape of Sound: An Adaptive Framework for Learning Voice-Face Association
Targeting at (a), we propose a two-level modality alignment loss where both global and local information are considered.
