mlsanityData to 7 Oct 2026

Coreset-Based Neural Network Compression

arXiv 1807.09810 ↗First posted 25 Jul 2018cs.CV cs.LGcited by 27

Not on the map. Why?

Abstract (arXiv)

We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to obtain compression. Our method requires no retraining, is easy to implement, and obtains state-of-the-art compression performance across a wide variety of CNN architectures. Coupled with quantization and Huffman coding, we create networks that provide AlexNet-like accuracy, with a memory footprint that is 832× smaller than the original AlexNet, while also introducing significant reductions in inference time as well. Additionally these compressed networks when fine-tuned, successfully generalize to other domains as well.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 3; 2023: 7; 2024: 3; 2025: 5; 2026: 2.

27 papers.

Sort:

By area:

  1. 2023A Simple and Effective Pruning Approach for Large Language Modelscited by 776
  2. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  3. 2021Towards Compact CNNs via Collaborative Compressioncited by 36
  4. 2022FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classificationcited by 30
  5. 2025Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observationscited by 19
  6. 2023Automatic Attention Pruning: Improving and Automating Model Pruning using Attentionscited by 11
  7. 2021Coresets for Decision Trees of Signalscited by 10
  8. 2025Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Accelerationcited by 9
  9. 2022Compressing Models with Few Samples: Mimicking then Replacingcited by 8
  10. 2022LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsificationcited by 7
  11. 2021Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusioncited by 5
  12. 2024Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networkscited by 4
15 more
  1. 2021A Deeper Look into Convolutions via Eigenvalue-based Pruningcited by 2
  2. 2021Efficient Inference via Universal LSH Kernelcited by 2
  3. 2021Batch Normalization Tells You Which Filter is Importantcited by 2
  4. 2023Filter Pruning based on Information Capacity and Independencecited by 2
  5. 2023Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detectioncited by 2
  6. 2024From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networkscited by 2
  7. 2025Training-Free Restoration of Pruned Neural Networkscited by 2
  8. 2021Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systemscited by 1
  9. 2023Securing Neural Networks with Knapsack Optimizationcited by 1
  10. 2023A Differentiable Framework for End-to-End Learning of Hybrid Structured Compressioncited by 1
  11. 2025Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrumcited by 1
  12. 2025Improving Model Classification by Optimizing the Training Datasetcited by 1
  13. 2024A Comprehensive Study of Structural Pruning for Vision Modelscited by 0
  14. 2026Deterministic Coreset for Lp Subspacecited by 0
  15. 2026Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifoldscited by 0