Hyperbolic Vision Transformers: Combining Improvements in Metric Learning
Metric learning aims to learn a highly discriminative model encouraging the embeddings of similar classes to be close in the chosen metrics and pushed apart for dissimilar ones. The common recipe is to use an encoder to extract embeddings and a distance-based loss function to match the representations -- usually, the Euclidean distance is utilized. An emerging interest in learning hyperbolic data embeddings suggests that hyperbolic geometry can be beneficial for natural data. Following this line of work, we propose a new hyperbolic-based model for metric learning. At the core of our method is a vision transformer with output embeddings mapped to hyperbolic space. These embeddings are directly optimized using modified pairwise cross-entropy loss. We evaluate the proposed model with six different formulations on four datasets achieving the new state-of-the-art performance. The source code is available at https://github.com/htdt/hyp_metric.
Code (2)
Tasks
Metric LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Understanding Hyperbolic Metric Learning through Hard Negative Sampling
In recent years, there has been a growing trend of incorporating hyperbolic geometry methods into computer vision. While these methods have achieved state-of-the-art performance on various metric learning tasks using hyp…
Metric LearningHexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation
Data across modalities such as images, text, and graphs often contains hierarchical and relational structures, which are challenging to model within Euclidean geometry. Hyperbolic geometry provides a natural framework fo…
Image ClassificationHyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules
Hyperbolic neural networks have emerged as a powerful tool for modeling hierarchical data across diverse modalities. Recent studies show that token distributions in foundation models exhibit scale-free properties, sugges…
RAGRobust Hyperbolic Learning with Curvature-Aware Optimization
Hyperbolic deep learning has become a growing research direction in computer vision due to the unique properties afforded by the alternate embedding space. The negative curvature and exponentially growing distance metric…
EEGMetric LearningCAT: Curvature-Adaptive Transformers for Geometry-Aware Learning
Transformers achieve strong performance across diverse domains but implicitly assume Euclidean geometry in their attention mechanisms, limiting their effectiveness on data with non-Euclidean structure. While recent exten…
Knowledge Graph CompletionRelational Reasoning