Research map / Label-efficient and robust learning / Semi-supervised learning
Dual Swap Disentangling
Zunlei Feng, Xinchao Wang, Chenglong Ke, An-Xiang Zeng, Dacheng Tao, Mingli Song
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add dual swap (swap and swap back) on unlabeled pairs instead of plain autoencoding them (ablation) | DSD · MNIST code classification, supervision rates 0.0-1.0 | classification accuracy | Improved |
| reduce supervision rate of paired samples from 100% to 20% (ablation) | DSD · MNIST code classification | classification accuracy | No clear effect |
| lower supervision rate with long training (ablation) | DSD · MNIST validation loss | validation loss | Hurt |
| DSD(0.5) vs plain Autoencoder, identity part of code | MNIST kNN classifier · MNIST | accuracy (identity part): 0.66 -> 0.76 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- InfoGAN — InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (NeurIPS 2016) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Weakly Supervised Disentanglement by Pairwise Similarities (AAAI 2020 · similarity 0.87)
- Weakly-Supervised Disentanglement Without Compromises (ICML 2020 · similarity 0.86)
- Weakly Supervised Disentanglement with Guarantees (ICLR 2020 · similarity 0.85)
- Disentangled Representation Learning via Flow Matching (NeurIPS 2026 · similarity 0.83)
- Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models (NeurIPS 2024 · similarity 0.83)
- Disentangled Representation Learning via Modular Compositional Bias (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
