Research map / Architectures and efficiency / RNNs and normalization
Asymmetric Gained Deep Image Compression With Continuous Rate Adaptation
Check 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 |
|---|---|---|---|
| Add gain units and inverse gain units for discrete rate adjustment | VAE-based image compression · Kodak | rate-distortion performance | Helped |
| Use exponent interpolation between trained gain-vector pairs | AG-VAE · Continuous rate range | rate-distortion performance | No clear effect |
| Add gain units to the Ballé et al. or Minnen et al. backbone (ablation) | VAE-based image compression · Kodak | rate-distortion performance | No clear effect |
| Add gain units to the hyperprior autoencoder (ablation) | CVR · Kodak | rate-distortion performance | Helped |
| Use an asymmetric Gaussian entropy model instead of a symmetric Gaussian model (ablation) | AG-VAE · Kodak, 0.4 to 0.6 bpp | rate-distortion performance | Helped |
| Use gain units and inverse gain units instead of bottleneck scaling | VAE-based image compression · Kodak | rate-distortion performance | Helped |
Closest papers by meaning
- Variational image compression with a scale hyperprior (ICLR 2018 · similarity 0.88)
- GLIC: General Format Learned Image Compression (AAAI 2025 · similarity 0.86)
- Towards Backward-Compatible Continual Learning of Image Compression (CVPR 2024 · similarity 0.86)
- Causal Context Adjustment Loss for Learned Image Compression (NeurIPS 2024 · similarity 0.85)
- Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec (NeurIPS 2024 · similarity 0.85)
- Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation (ICLR 2025 · similarity 0.85)
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.