Disentanglement of Color and Shape Representations for Continual Learning

13 Jul 2020  ·  David Berga, Marc Masana, Joost Van de Weijer ·

We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture... We tested classification accuracy and forgetting in a task-incremental setting with Oxford-102 Flowers dataset. We combine our method with Elastic Weight Consolidation, Learning without Forgetting, Synaptic Intelligence and Memory Aware Synapses, and show that feature disentanglement positively impacts continual learning performance. read more

PDF Abstract
No code implementations yet. Submit your code now


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here