Continual Hyperbolic Learning of Instances and Classes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911002159742976 |
|---|---|
| author | Ayoughi, Melika Atigh, Mina Ghadimi Derakhshani, Mohammad Mahdi Snoek, Cees G. M. Mettes, Pascal Groth, Paul |
| author_facet | Ayoughi, Melika Atigh, Mina Ghadimi Derakhshani, Mohammad Mahdi Snoek, Cees G. M. Mettes, Pascal Groth, Paul |
| contents | Continual learning has traditionally focused on classifying either instances or classes, but real-world applications, such as robotics and self-driving cars, require models to handle both simultaneously. To mirror real-life scenarios, we introduce the task of continual learning of instances and classes, at the same time. This task challenges models to adapt to multiple levels of granularity over time, which requires balancing fine-grained instance recognition with coarse-grained class generalization. In this paper, we identify that classes and instances naturally form a hierarchical structure. To model these hierarchical relationships, we propose HyperCLIC, a continual learning algorithm that leverages hyperbolic space, which is uniquely suited for hierarchical data due to its ability to represent tree-like structures with low distortion and compact embeddings. Our framework incorporates hyperbolic classification and distillation objectives, enabling the continual embedding of hierarchical relations. To evaluate performance across multiple granularities, we introduce continual hierarchical metrics. We validate our approach on EgoObjects, the only dataset that captures the complexity of hierarchical object recognition in dynamic real-world environments. Empirical results show that HyperCLIC operates effectively at multiple granularities with improved hierarchical generalization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10710 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Continual Hyperbolic Learning of Instances and Classes Ayoughi, Melika Atigh, Mina Ghadimi Derakhshani, Mohammad Mahdi Snoek, Cees G. M. Mettes, Pascal Groth, Paul Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Continual learning has traditionally focused on classifying either instances or classes, but real-world applications, such as robotics and self-driving cars, require models to handle both simultaneously. To mirror real-life scenarios, we introduce the task of continual learning of instances and classes, at the same time. This task challenges models to adapt to multiple levels of granularity over time, which requires balancing fine-grained instance recognition with coarse-grained class generalization. In this paper, we identify that classes and instances naturally form a hierarchical structure. To model these hierarchical relationships, we propose HyperCLIC, a continual learning algorithm that leverages hyperbolic space, which is uniquely suited for hierarchical data due to its ability to represent tree-like structures with low distortion and compact embeddings. Our framework incorporates hyperbolic classification and distillation objectives, enabling the continual embedding of hierarchical relations. To evaluate performance across multiple granularities, we introduce continual hierarchical metrics. We validate our approach on EgoObjects, the only dataset that captures the complexity of hierarchical object recognition in dynamic real-world environments. Empirical results show that HyperCLIC operates effectively at multiple granularities with improved hierarchical generalization. |
| title | Continual Hyperbolic Learning of Instances and Classes |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2506.10710 |