Prototype Augmented Hypernetworks for Continual Learning

MCML Authors

Cecilia Curreli

→ Group Daniel Cremers
 Computer Vision & Artificial Intelligence

Daniel Cremers

Prof. Dr.

Director

Computer Vision & Artificial Intelligence

Abstract

Continual learning (CL) aims to learn a sequence of tasks without forgetting prior knowledge, but gradient updates for a new task often overwrite the weights learned earlier, causing catastrophic forgetting (CF). We propose Prototype-Augmented Hypernetworks (PAH), a framework where a single hypernetwork, conditioned on learnable task prototypes, dynamically generates task-specific classifier heads on demand. To mitigate forgetting, PAH combines cross-entropy with dual distillation losses, one to align logits and another to align prototypes, ensuring stable feature representations across tasks. Evaluations on Split-CIFAR100 and TinyImageNet demonstrate that PAH achieves state-of-the-art performance, reaching 74.5% and 63.7% accuracy with only 1.7% and 4.4% forgetting, respectively, surpassing prior methods without storing samples or heads.

misc

---

Preprint

May. 2025

---

Authors

N. De La Fuente • M. Pilligua • D. Vidal • A. Soutiff • C. Curreli • D. Cremers • A. Barsky

---

Links

---

Research Area

 B1 | Computer Vision