# Disentanglement of Color and Shape Representations for Continual Learning

arXiv: https://arxiv.org/abs/2007.06356 · HTML: https://mlsanity.com/paper/2007.06356/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 2 of 2)

- [Continual learning in cross-modal retrieval](https://mlsanity.com/paper/2104.06806/) (2021)
- [Federated Self-Supervised Learning of Monocular Depth Estimators for Autonomous Vehicles](https://mlsanity.com/paper/2310.04837/) (2023)

## Abstract (arXiv)

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.