Research map / Architectures and efficiency / Quantization
SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization
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 |
|---|---|---|---|
| Use 4-bit quantized prediction to guide sparse inference | SeerNet · ILSVRC-2012 | top-1 accuracy (%): 71.59 -> 71.31 | Hurt |
| Use 4-bit quantized prediction to guide sparse inference | SeerNet · CIFAR-10 | top-1 accuracy (%): 93.91 -> 93.88 | Hurt |
| Use output sparsity to skip dense convolution work | SeerNet · ILSVRC-2012 | speedup: 30.0% | Helped |
| Use 2-bit rather than 4-bit quantization for prediction (ablation) | SeerNet · ILSVRC-2012 | top-1 accuracy (%) | Hurt |
| Use 4-bit rather than 8-bit quantization for prediction (ablation) | SeerNet · ILSVRC-2012 | top-1 accuracy (%) | Hurt |
| Fuse convolution and batch normalization before quantization (ablation) | SeerNet on VGG16 BN · ILSVRC-2012 | top-1 accuracy (%): 66.70 -> 72.85 | Helped |
| Fuse convolution and batch normalization before quantization (ablation) | SeerNet on VGG16 BN · ILSVRC-2012 | top-5 accuracy (%): 87.29 -> 91.18 | Helped |
| Apply 4-bit rather than 16-bit quantization to fused Conv-BN (ablation) | SeerNet on VGG16 BN · ILSVRC-2012 | top-1 accuracy (%): 73.36 -> 72.85 | Hurt |
Closest papers by meaning
- Effective Interplay between Sparsity and Quantization: From Theory to Practice (ICLR 2025 · similarity 0.90)
- On Implicit Filter Level Sparsity in Convolutional Neural Networks (CVPR 2019 · similarity 0.89)
- Inducing and Exploiting Activation Sparsity for Fast Inference on Deep Neural Networks (ICML 2020 · similarity 0.89)
- Focused Quantization for Sparse CNNs (NeurIPS 2019 · similarity 0.88)
- Faster CNNs with Direct Sparse Convolutions and Guided Pruning (ICLR 2017 · similarity 0.88)
- Accelerating Sparse Convolution with Column Vector-Wise Sparsity (NeurIPS 2022 · similarity 0.88)
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.