Modular Representations for Weak Disentanglement
Not on the map. Why?
Abstract (arXiv)
The recently introduced weakly disentangled representations proposed to relax some constraints of the previous definitions of disentanglement, in exchange for more flexibility. However, at the moment, weak disentanglement can only be achieved by increasing the amount of supervision as the number of factors of variations of the data increase. In this paper, we introduce modular representations for weak disentanglement, a novel method that allows to keep the amount of supervised information constant with respect the number of generative factors. The experiments shows that models using modular representations can increase their performance with respect to previous work without the need of additional supervision.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 12 Sep 2022.
Builds on
12 of 18 references.
References · 12
- 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
- 2018Disentangling by Factorisingcited by 614
- 2018Understanding disentangling in β-VAEcited by 332
- 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
- 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
- 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
- 2019Disentangling Factors of Variation Using Few Labelscited by 57
- 2019Theory and Evaluation Metrics for Learning Disentangled Representationscited by 57
- 2021Contrastively Disentangled Sequential Variational Autoencodercited by 34
- 2021An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wildcited by 30
- 2019Weakly Supervised Disentanglement by Pairwise Similaritiescited by 22
- 2022Leveraging Relational Information for Learning Weakly Disentangled Representationscited by 5
Built on by
Not cited yet.