Research map / Image generation / Autoregressive and latent generation
Conditional Image Generation with PixelCNN Decoders
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace PixelCNN rectified linear activations with gated activations | PixelCNN · CIFAR-10 | NLL (bits/dim): 3.14 -> 3.03 | Helped |
| Use gated convolutional layers and dual stacks | Gated PixelCNN · ImageNet 32x32 | NLL (bits/dim): 3.86 -> 3.83 | Helped |
| Use gated convolutional layers and dual stacks | Gated PixelCNN · ImageNet 64x64 | NLL (bits/dim): 3.63 -> 3.57 | Helped |
| Add a residual connection in the vertical stack (ablation) | Gated PixelCNN · Initial experiments | results | No clear effect |
| Condition image generation on ImageNet class labels | Conditional PixelCNN · ImageNet class-conditional modeling | log-likelihood | No clear effect |
Closest papers by meaning
- PixelNN: Example-based Image Synthesis (ICLR 2018 · similarity 0.89)
- CcGAN: Continuous Conditional Generative Adversarial Networks for Image Generation (ICLR 2021 · similarity 0.88)
- High-Fidelity Image Generation With Fewer Labels (ICML 2019 · similarity 0.88)
- PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications (ICLR 2017 · similarity 0.87)
- Robust Conditional Generative Adversarial Networks (ICLR 2019 · similarity 0.87)
- PixelCNN Models with Auxiliary Variables for Natural Image Modeling (ICML 2017 · similarity 0.87)
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.