Research map / Image generation / Editing and style transfer
Understanding Degeneracies and Ambiguities in Attribute Transfer
Attila Szabo, Qiyang Hu, Tiziano Portenier, Matthias Zwicker, Paolo Favaro
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 |
|---|---|---|---|
| use instance normalization instead of no normalization (ablation) | adversarial disentangling autoencoder · ShapeNet cars, car type NN classification | mAP: 0.13 -> 0.20 | Improved |
| use instance normalization instead of batch normalization (ablation) | adversarial disentangling autoencoder · ShapeNet cars, car type NN classification | mAP: 0.08 -> 0.20 | Improved |
| use batch or instance normalization instead of none (ablation) | adversarial disentangling autoencoder · ShapeNet cars, viewpoint NN classification | mAP: 0.47 -> 0.50 | Improved |
| use batch normalization instead of none (ablation) | adversarial disentangling autoencoder · ShapeNet cars, car type NN classification | mAP: 0.13 -> 0.08 | Hurt |
| add adversarial term L_GAN to autoencoder loss, with large Nv dimension (ablation) | L_AE · ShapeNet cars attribute transfer | transfer quality / viewpoint mAP vs Nv size | Improved |
| increase Nv feature dimension (2 to 128) with autoencoder loss only (ablation) | L_AE · ShapeNet cars attribute transfer | transfer quality | Hurt |
Closest papers by meaning
- Asking Friendly Strangers: Non-Semantic Attribute Transfer (AAAI 2018 · similarity 0.88)
- Disentangling Factors of Variation by Mixing Them (CVPR 2018 · similarity 0.86)
- Multi-Attribute Transfer via Disentangled Representation (AAAI 2019 · similarity 0.86)
- Scaling-Up Disentanglement for Image Translation (ICCV 2021 · similarity 0.86)
- Learning Attributes Equals Multi-Source Domain Generalization (CVPR 2016 · similarity 0.86)
- Disentangled Representation Learning via Modular Compositional Bias (NeurIPS 2025 · similarity 0.84)
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.
