Continual Hyperbolic Learning of Instances and Classes

TL;DR

This paper introduces HyperCLIC, a hyperbolic space-based continual learning algorithm that effectively models hierarchical relationships for simultaneous instance and class recognition in dynamic environments.

Contribution

It proposes a novel continual learning framework leveraging hyperbolic geometry to handle hierarchical data at multiple granularities, validated on a complex real-world dataset.

Findings

HyperCLIC outperforms baselines in hierarchical generalization.

The hyperbolic embedding effectively captures hierarchical relationships.

The approach adapts well to dynamic, real-world environments.

Abstract

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.