Research map / Image generation / GANs
Adversarial Learning with Local Coordinate Coding
Jiezhang Cao, Yong Guo, Qingyao Wu, Chunhua Shen, Junzhou Huang, Mingkui Tan
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 |
|---|---|---|---|
| Replace the standard prior sampling with LCC sampling | GANs · Oxford-102 | Inception Score: 2.66 -> 2.71 | Improved |
| Use LCC sampling with d=30 instead of the baseline prior | GANs · MNIST | MS-SSIM: 0.239 -> 0.224 | Improved |
| Use LCC sampling with d=30 instead of the baseline prior | GANs · Oxford-102 | MS-SSIM: 0.151 -> 0.153 | Mixed |
| Use LCC sampling with d=30 instead of the baseline prior | GANs · LSUN | MS-SSIM: 0.213 -> 0.203 | Improved |
| Use LCC sampling with d=30 instead of the baseline prior | GANs · CelebA | MS-SSIM: 0.308 -> 0.305 | Improved |
| Replace sparse coding with LCC coding | GANs · Oxford-102 (d=5) | Inception Score: 2.44 -> 2.57 | Improved |
| Replace sparse coding with LCC coding | GANs · Oxford-102 (d=10) | MS-SSIM: 0.179 -> 0.163 | Improved |
| Increase the LCC input dimension from d=30 to d=100 (ablation) | LCC-GANs · Oxford-102 | Inception Score: 2.83 -> 2.75 | Mixed |
| Increase the LCC input dimension from d=30 to d=100 (ablation) | LCC-GANs · Oxford-102 | MS-SSIM: 0.153 -> 0.147 | Improved |
| Use a smaller input dimension, d=10 instead of d=100 (ablation) | LCC-GANs · Oxford-102 | Inception Score: 2.75 -> 2.71 | Mixed |
| Use LCC coding rather than sampling directly from a standard Gaussian | Progressive GANs · CelebA | visual image quality | Improved |
| Use LCC sampling rather than standard prior sampling at low dimension | GANs · MNIST (d=3) | visual diversity | Improved |
Closest papers by meaning
- Improving Generative Adversarial Networks With Local Coordinate Coding (TPAMI 2020 · similarity 0.97)
- Uncertainty Principles of Encoding GANs (ICML 2021 · similarity 0.88)
- CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction (ECCV 2024 · similarity 0.88)
- Collaborative Sampling in Generative Adversarial Networks (AAAI 2020 · similarity 0.87)
- Improving GAN with Neighbors Embedding and Gradient Matching (AAAI 2019 · similarity 0.87)
- Improving Generalization and Stability of Generative Adversarial Networks (ICLR 2019 · 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.
