Research map / Architectures and efficiency / Quantization
Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks
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 explicit loss-error-aware quantization instead of quantization based only on weight reconstruction error | DNN weight quantization · ImageNet | classification accuracy | Helped |
| Use loss-error-aware quantization | DNN quantization · CIFAR-10 | classification accuracy | Helped |
| Use the proposed quantization approach rather than uniform quantization | DNN quantization · ImageNet | classification accuracy | Helped |
Closest papers by meaning
- Adaptive Loss-Aware Quantization for Multi-Bit Networks (CVPR 2020 · similarity 0.92)
- Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights (ICLR 2017 · similarity 0.92)
- Adaptive Quantization of Neural Networks (ICLR 2018 · similarity 0.91)
- Loss-aware Weight Quantization of Deep Networks (ICLR 2018 · similarity 0.91)
- Gradient $\ell_1$ Regularization for Quantization Robustness (ICLR 2020 · similarity 0.91)
- One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training (AAAI 2024 · similarity 0.89)
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.