← Search

Yanqi Ge

2 accepted papers

2024

Beyond Prototypes: Semantic Anchor Regularization for Better Representation Learning

AAAI 2024technical

One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. Many outstanding metric-based and prototype-based methods following the Expectation-Maximization paradigm, have been proposed for this objective. However, they inevita…

2024

Beyond Viewpoint: Robust 3D Object Recognition under Arbitrary Views through Joint Multi-Part Representation

ECCV 2024poster

"Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different viewpoint positions and quantities, and their poses are not al…

Cited by 1SourcePDFScholar