mlsanityData to 7 Oct 2026

SW-VAE: Weakly Supervised Learn Disentangled Representation Via Latent Factor Swapping

arXiv 2209.10623 ↗First posted 21 Sep 2022cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

Representation disentanglement is an important goal of representation learning that benefits various downstream tasks. To achieve this goal, many unsupervised learning representation disentanglement approaches have been developed. However, the training process without utilizing any supervision signal have been proved to be inadequate for disentanglement representation learning. Therefore, we propose a novel weakly-supervised training approach, named as SW-VAE, which incorporates pairs of input observations as supervision signals by using the generative factors of datasets. Furthermore, we introduce strategies to gradually increase the learning difficulty during training to smooth the training process. As shown on several datasets, our model shows significant improvement over state-of-the-art (SOTA) methods on representation disentanglement tasks.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 34 references that are in the map. First posted on arXiv 21 Sep 2022.

Builds on

22 of 34 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  9. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  10. 2018Disentangling by Factorisingcited by 614
  11. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  12. 2018Understanding disentangling in β-VAEcited by 332
10 more
  1. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  2. 2020Weakly-Supervised Disentanglement Without Compromisescited by 237
  3. 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
  4. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  5. 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
  6. 2019Are Disentangled Representations Helpful for Abstract Visual Reasoning?cited by 100
  7. 2019On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Datasetcited by 100
  8. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  9. 2019Weakly Supervised Disentanglement by Pairwise Similaritiescited by 22
  10. 2018Dual Swap Disentanglingcited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 0; 2026: 1.

3 papers.

  1. 2023Modeling Complex Disease Trajectories using Deep Generative Models with Semi-Supervised Latent Processescited by 2
  2. 2024Semi-Supervised Generative Models for Disease Trajectories: A Case Study on Systemic Sclerosiscited by 0
  3. 2026XFACTORS: Disentangled Information Bottleneck via Contrastive Supervisioncited by 0