mlsanityData to 7 Oct 2026

PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions

arXiv 1504.08362 ↗First posted 30 Apr 2015cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such as mobile phones. Inspired by the loop perforation technique from source code optimization, we speed up the bottleneck convolutional layers by skipping their evaluation in some of the spatial positions. We propose and analyze several strategies of choosing these positions. We demonstrate that perforation can accelerate modern convolutional networks such as AlexNet and VGG-16 by a factor of 2x - 4x. Additionally, we show that perforation is complementary to the recently proposed acceleration method of Zhang et al.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Apr 2015.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 3; 2023: 2; 2024: 3; 2025: 1.

17 papers.

Sort:

  1. 2021Zero-Cost Proxies for Lightweight NAScited by 194
  2. 2024AtP*: An efficient and scalable method for localizing LLM behaviour to componentscited by 100
  3. 2021Spatially-Adaptive Image Restoration using Distortion-Guided Networkscited by 77
  4. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
  5. 2021PnP-DETR: Towards Efficient Visual Analysis with Transformerscited by 52
  6. 2021Stealthy Backdoors as Compression Artifactscited by 17
  7. 2024ESOD: Efficient Small Object Detection on High-Resolution Imagescited by 15
  8. 2023Tensor Decomposition for Model Reduction in Neural Networks: A Reviewcited by 14
  9. 2024ShadowLLM: Predictor-based Contextual Sparsity for Large Language Modelscited by 13
  10. 2022Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectorscited by 10
  11. 2021Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNNcited by 9
  12. 2021Neural Architecture Search as Program Transformation Explorationcited by 8
5 more
  1. 2022Survey: Exploiting Data Redundancy for Optimization of Deep Learningcited by 6
  2. 2021Learning Versatile Convolution Filters for Efficient Visual Recognitioncited by 3
  3. 2025GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMscited by 1
  4. 2022Mixture-of-Rookies: Saving DNN Computations by Predicting ReLU Outputscited by 0
  5. 2023Mobiprox: Supporting Dynamic Approximate Computing on Mobilescited by 0