Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Compression with Bayesian Implicit Neural Representations
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 |
|---|---|---|---|
| learn the model prior instead of using a layer-wise zero-mean isotropic Gaussian prior (ablation) | COMBINER · CIFAR-10 | PSNR: 4dB | Helped |
| add posterior fine-tuning between A* coding blocks (ablation) | COMBINER · CIFAR-10 | PSNR | Helped |
| use A* coding approximate samples rather than exact posterior samples (ablation) | COMBINER · CIFAR-10 | PSNR: 0.8 -- 1.3dB | Hurt |
| compress audio as one datum rather than cropping it into chunks (ablation) | COMBINER · LibriSpeech test-clean | PSNR: around 5 dB | Helped |
| reduce posterior fine-tuning from around 30k iterations to 3k iterations (ablation) | COMBINER · CIFAR-10 | reconstruction quality: 0.3 dB | Hurt |
Closest papers by meaning
- Variational Bayesian Quantization (ICML 2020 · similarity 0.89)
- Improving Inference for Neural Image Compression (NeurIPS 2020 · similarity 0.88)
- Robustly overfitting latents for flexible neural image compression (NeurIPS 2024 · similarity 0.87)
- Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding (ICLR 2025 · similarity 0.86)
- Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesis (CVPR 2024 · similarity 0.86)
- Progressive Compression with Universally Quantized Diffusion Models (ICLR 2025 · similarity 0.86)
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.