Realistic Continual Learning Approach using Pre-trained Models
cs.LG, cs.CV
Submitted: 2024-04-11
Updated: 2026-09-14
Journal ref: Journal of Visual Communication and Image Representation, 2026
DOI: 10.1016/j.jvcir.2026.104970
Code: https://github.com/gramuah/clare
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
- LoRA: Low-Rank Adaptation of Large Language Models
- Visual Prompt Tuning
- Three scenarios for continual learning
- Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Need
- M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks