Research map / Architectures and efficiency / Quantization
Quicker ADC : Unlocking the Hidden Potential of Product Quantization With SIMD
Fabien André, Anne-Marie Kermarrec, Nicolas Le Scouarnec
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 |
|---|---|---|---|
| use 5-bit subquantizers with padding instead of 4-bit (ablation) | 64-bit PQ · SIFT1M exhaustive search | R@1: 0.159 -> 0.153 | Hurt |
| use irregular PQ 12x{6,6,4} instead of 16x4 PQ | 64-bit PQ · SIFT1M exhaustive search | R@1: 0.158 -> 0.179 | Improved |
| use irregular PQ 12x{6,5,5} instead of 16x4 PQ | 64-bit PQ · SIFT1M exhaustive search | R@1: 0.158 -> 0.174 | Improved |
Closest papers by meaning
- Product Quantized Translation for Fast Nearest Neighbor Search (AAAI 2018 · similarity 0.88)
- Efficient Large-Scale Approximate Nearest Neighbor Search on the GPU (CVPR 2016 · similarity 0.88)
- Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search (ICCV 2021 · similarity 0.87)
- Efficient Large-Scale Approximate Nearest Neighbor Search on OpenCL FPGA (CVPR 2018 · similarity 0.86)
- Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks (ICLR 2025 · similarity 0.84)
- Reshape and Adapt for Output Quantization (RAOQ): Quantization-aware Training for In-memory Computing Systems (ICML 2024 · similarity 0.84)
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.
