Search Results

Exemplar-free class incremental learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recently in this setting due to their impressive performances and lower ...

When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones. Using a small memory containing ...

• Proposed to use Balanced Softmax for bias mitigation in class-incremental learning.
• Can be used for class-incremental learning with and without memory.
• Seamlessly combinable with state-of-the-art approaches to improve accuracy.

In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous. However, despite the ...

Deep neural networks are prone to catastrophic forgetting when incrementally trained on new classes or new tasks as adaptation to the new data leads to a drastic decrease of the performance on the old classes and tasks. By using a small memory for ...

In this paper, we introduce a novel layer designed to be used as the output of pre-trained neural networks in the context of classification. Based on Associative Memories, this layer can help design deep neural networks which support incremental ...