CVJan 26, 2025

On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning

arXiv:2501.15454v17 citationsh-index: 4IJCAI
Originality Incremental advance
AI Analysis

This work addresses the problem of catastrophic forgetting in machine learning for scenarios where storing old data is not feasible, representing an incremental advance in task-specific methods for CIL.

The paper tackled the challenge of exemplar-free class incremental learning (EF-CIL) by proposing DCNet, which maps class representations into a hyperspherical space for better discrimination and consistency, achieving state-of-the-art performance with concrete improvements in accuracy.

Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying any old class exemplars. An emerging theory-guided framework for CIL trains task-specific models for a shared network, shifting the pressure of forgetting to task-id prediction. In EF-CIL, task-id prediction is more challenging due to the lack of inter-task interaction (e.g., replays of exemplars). To address this issue, we conduct a theoretical analysis of the importance and feasibility of preserving a discriminative and consistent feature space, upon which we propose a novel method termed DCNet. Concretely, it progressively maps class representations into a hyperspherical space, in which different classes are orthogonally distributed to achieve ample inter-class separation. Meanwhile, it also introduces compensatory training to adaptively adjust supervision intensity, thereby aligning the degree of intra-class aggregation. Extensive experiments and theoretical analysis verified the superiority of the proposed DCNet.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes