Research map / Architectures and efficiency / Quantization
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible 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 |
|---|---|---|---|
| Use vector quantization instead of scalar quantization (ablation) | Soft-to-Hard Autoencoder · ImageNET100 | compression rate at a given reconstruction MSE | Helped |
| Add entropy loss (use β > 0 rather than β = 0) (ablation) | Soft-to-Hard Autoencoder · ImageNET100 | compression rate at a given reconstruction MSE | Helped |
| Use arithmetic coding instead of Huffman coding | Soft-to-Hard Annealing for 32-layer ResNet · CIFAR-10 | compression ratio: 19.15 -> 20.15 | Helped |
| Use end-to-end soft-to-hard annealing compression rather than the original uncompressed model | 32-layer ResNet · CIFAR-10 test | accuracy: 92.6 -> 92.1 | Hurt |
| Use end-to-end soft-to-hard annealing compression rather than pruning, uniform quantization, fine-tuning, and entropy coding | 32-layer ResNet · CIFAR-10 | compression ratio: 22.17 -> 19.15 | Hurt |
Closest papers by meaning
- Soft then Hard: Rethinking the Quantization in Neural Image Compression (ICML 2021 · similarity 0.91)
- Training with Quantization Noise for Extreme Model Compression (ICLR 2021 · similarity 0.88)
- Universally Quantized Neural Compression (NeurIPS 2020 · similarity 0.88)
- Focused Quantization for Sparse CNNs (NeurIPS 2019 · similarity 0.87)
- Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding (ICLR 2025 · similarity 0.86)
- Effective Interplay between Sparsity and Quantization: From Theory to Practice (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.