paper-with-me

홈 › Papers

Continual Hyperbolic Learning of Instances and Classes

2025-06-12 · Melika Ayoughi, Mina Ghadimi Atigh, Mohammad Mahdi Derakhshani, Cees G. M. Snoek, Pascal Mettes, Paul Groth

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.

📄 PDF Abstract BibTeX arXiv:2506.10710

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningObject RecognitionSelf-Driving Cars

Similar Papers 제목 키워드 기반

Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World Perception

2024-07-25 · Julia Hindel, Daniele Cattaneo, Abhinav Valada

Semantic segmentation models are typically trained on a fixed set of classes, limiting their applicability in open-world scenarios. Class-incremental semantic segmentation aims to update models with emerging new classes …

Autonomous DrivingClass-Incremental Semantic SegmentationContinual Semantic SegmentationIncremental Learning+2

Expanding continual few-shot learning benchmarks to include recognition of specific instances

2022-08-26 · Gideon Kowadlo, Abdelrahman Ahmed, Amir Mayan, David Rawlinson

Continual learning and few-shot learning are important frontiers in progress toward broader Machine Learning (ML) capabilities. Recently, there has been intense interest in combining both. One of the first examples to do…

continual few-shot learningContinual LearningFew-Shot LearningHippocampus

Continual Learning by Three-Phase Consolidation

2024-03-12 · Davide Maltoni, Lorenzo Pellegrini

TPC (Three-Phase Consolidation) is here introduced as a simple but effective approach to continually learn new classes (and/or instances of known classes) while controlling forgetting of previous knowledge. Each experien…

Continual Learning

Hyperbolic Dual Feature Augmentation for Open-Environment

2025-06-10 · Peilin Yu, Yuwei Wu, Zhi Gao, Xiaomeng Fan 외

Feature augmentation generates novel samples in the feature space, providing an effective way to enhance the generalization ability of learning algorithms with hyperbolic geometry. Most hyperbolic feature augmentation is…

class-incremental learningClass Incremental LearningFew-Shot Learningimage-classification+5

Continual Rare-Class Recognition with Emerging Novel Subclasses

2019-06-28 · Hung Nguyen, Xuejian Wang, Leman Akoglu

Given a labeled dataset that contains a rare (or minority) class of of-interest instances, as well as a large class of instances that are not of interest, how can we learn to recognize future of-interest instances over a…