Research map / Architectures and efficiency / Pruning and efficient tuning
HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact 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 |
|---|---|---|---|
| Apply HALOC low-rank compression and automatic rank selection | ResNet-20 · CIFAR-10 | Top-1 accuracy (%): 91.25 -> 91.32 | Helped |
| Apply HALOC low-rank compression and automatic rank selection | VGG-16 · CIFAR-10 | Top-1 accuracy (%): 92.78 -> 93.16 | Helped |
| Use HALOC instead of ALDS | ResNet-20 · CIFAR-10 | Top-1 accuracy (%): 90.92 -> 91.32 | Helped |
| Apply HALOC low-rank compression and automatic rank selection | ResNet-18 · ImageNet | Top-1 accuracy (%): 69.75 -> 70.65 | Helped |
| Use HALOC instead of ALDS | ResNet-18 · ImageNet | Top-1 accuracy (%): 69.22 -> 70.65 | Helped |
| Apply HALOC low-rank compression and automatic rank selection | MobileNetV2 · ImageNet | Top-1 accuracy (%): 71.85 -> 70.98 | Hurt |
| Use HALOC instead of ALDS | MobileNetV2 · ImageNet | Top-1 accuracy (%): 70.32 -> 70.98 | Helped |
| Apply HALOC hardware-aware low-rank compression | ResNet-18 · ImageNet, NVIDIA Tesla V100 | Throughput (images/s): 4362.1 -> 6360.5 | Helped |
| Apply HALOC hardware-aware low-rank compression | ResNet-18 · ImageNet, NVIDIA Jetson TX2 | Throughput (images/s): 86.3 -> 151.0 | Helped |
| Apply HALOC hardware-aware low-rank compression | ResNet-18 · ImageNet, ASIC Eyeriss | Throughput (images/s): 121.4 -> 247.0 | Helped |
| Add feature-map-based regularization that aligns compressed-layer activations with the original model (ablation) | HALOC · ResNet-18, ImageNet | Final accuracy | Helped |
Closest papers by meaning
- DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks (ICML 2022 · similarity 0.88)
- Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition (NeurIPS 2021 · similarity 0.88)
- Efficient Neural Network Compression (CVPR 2019 · similarity 0.88)
- Low-Rank Compression of Neural Nets: Learning the Rank of Each Layer (CVPR 2020 · similarity 0.87)
- BATUDE: Budget-Aware Neural Network Compression Based on Tucker Decomposition (AAAI 2022 · similarity 0.87)
- Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks (NeurIPS 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.