mlsanityData to 7 Oct 2026

Post-training deep neural network pruning via layer-wise calibration

arXiv 2104.15023 ↗First posted 30 Apr 2021cs.CV cs.AI cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

We present a post-training weight pruning method for deep neural networks that achieves accuracy levels tolerable for the production setting and that is sufficiently fast to be run on commodity hardware such as desktop CPUs or edge devices. We propose a data-free extension of the approach for computer vision models based on automatically-generated synthetic fractal images. We obtain state-of-the-art results for data-free neural network pruning, with ~1.5% top@1 accuracy drop for a ResNet50 on ImageNet at 50% sparsity rate. When using real data, we are able to get a ResNet50 model on ImageNet with 65% sparsity rate in 8-bit precision in a post-training setting with a ~1% top@1 accuracy drop. We release the code as a part of the OpenVINO(TM) Post-Training Optimization tool.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

18 of 23 references.

References · 18

  1. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  2. 2020Up or Down? Adaptive Rounding for Post-Training Quantizationcited by 600
  3. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 596
  4. 2020What is the State of Neural Network Pruning?cited by 578
  5. 2019The State of Sparsity in Deep Neural Networkscited by 471
  6. 2021BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstructioncited by 464
  7. 2018AMC: AutoML for Model Compression and Acceleration on Mobile Devicescited by 375
  8. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
  9. 2019Data-Free Quantization Through Weight Equalization and Bias Correctioncited by 328
  10. 2020Soft Threshold Weight Reparameterization for Learnable Sparsitycited by 150
  11. 2015Data-free parameter pruning for Deep Neural Networkscited by 112
  12. 2021Pre-training without Natural Imagescited by 100
6 more
  1. 2020Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programmingcited by 89
  2. 2019Fast Sparse ConvNetscited by 86
  3. 2020EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruningcited by 80
  4. 2021Can Vision Transformers Learn without Natural Images?cited by 32
  5. 2020Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsitycited by 30
  6. 2020Layer-Wise Data-Free CNN Compressioncited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 6; 2024: 6; 2025: 4; 2026: 3.

23 papers.

Sort:

By area:

  1. 2022A Fast Post-Training Pruning Framework for Transformerscited by 161
  2. 2023ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Modelscited by 19
  3. 2023Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networkscited by 15
  4. 2023Accurate Retraining-free Pruning for Pretrained Encoder-based Language Modelscited by 11
  5. 2024Structurally Prune Anything: Any Architecture, Any Framework, Any Timecited by 8
  6. 2025EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Modelscited by 7
  7. 2024PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Modelscited by 5
  8. 2023Lossy and Lossless (L2) Post-training Model Size Compressioncited by 4
  9. 2023Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillationcited by 4
  10. 2022SVD-NAS: Coupling Low-Rank Approximation and Neural Architecture Searchcited by 3
  11. 2022QFT: Post-training quantization via fast joint finetuning of all degrees of freedomcited by 3
  12. 2024Generalizability of Mixture of Domain-Specific Adapters from the Lens of Signed Weight Directions and its Application to Effective Model Pruningcited by 3
11 more
  1. 2024Fast and Controllable Post-training Sparsity: Learning Optimal Sparsity Allocation with Global Constraint in Minutescited by 3
  2. 2024STAT: Shrinking Transformers After Trainingcited by 2
  3. 2025Onboard Optimization and Learning: A Surveycited by 1
  4. 2025Spatio-Temporal Pruning for Compressed Spiking Large Language Modelscited by 1
  5. 2025Theoretical Compression Bounds for Wide Multilayer Perceptronscited by 1
  6. 2026Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networkscited by 1
  7. 2022Pruning On-the-Fly: A Recoverable Pruning Method without Fine-tuningcited by 0
  8. 2023Post-training Model Quantization Using GANs for Synthetic Data Generationcited by 0
  9. 2024TinySeg: Model Optimizing Framework for Image Segmentation on Tiny Embedded Systemscited by 0
  10. 2026How Sparsity Allocation Shapes Label-Free Post-Pruning Recoverabilitycited by 0
  11. 2026Relative Repairability: A Calibration-Based Diagnostic for High-Sparsity Post-Pruning Allocationcited by 0