Continual Learning with Pretrained Backbones by Tuning in the Input Space.

Simone Marullo Matteo Tiezzi Marco Gori Stefano Melacci Tinne Tuytelaars

Published in: IJCNN (2023)

Keyphrases

input space
learning algorithm
learning problems
learning process
data sets
learning tasks
class labels
information extraction
supervised learning
multi task learning
labeled data
unsupervised learning
active learning
prior knowledge
high dimensional
reinforcement learning
training data
neural network