# PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions

arXiv: https://arxiv.org/abs/1504.08362 · HTML: https://mlsanity.com/paper/1504.08362/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2015.

## Built on by (most cited first, 17 of 17)

- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [AtP*: An efficient and scalable method for localizing LLM behaviour to components](https://mlsanity.com/paper/2403.00745/) (2024)
- [Spatially-Adaptive Image Restoration using Distortion-Guided Networks](https://mlsanity.com/paper/2108.08617/) (2021)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [PnP-DETR: Towards Efficient Visual Analysis with Transformers](https://mlsanity.com/paper/2109.07036/) (2021)
- [Stealthy Backdoors as Compression Artifacts](https://mlsanity.com/paper/2104.15129/) (2021)
- [ESOD: Efficient Small Object Detection on High-Resolution Images](https://mlsanity.com/paper/2407.16424/) (2024)
- [Tensor Decomposition for Model Reduction in Neural Networks: A Review](https://mlsanity.com/paper/2304.13539/) (2023)
- [ShadowLLM: Predictor-based Contextual Sparsity for Large Language Models](https://mlsanity.com/paper/2406.16635/) (2024)
- [Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors](https://mlsanity.com/paper/2208.11356/) (2022)
- [Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN](https://mlsanity.com/paper/2107.14444/) (2021)
- [Neural Architecture Search as Program Transformation Exploration](https://mlsanity.com/paper/2102.06599/) (2021)
- [Survey: Exploiting Data Redundancy for Optimization of Deep Learning](https://mlsanity.com/paper/2208.13363/) (2022)
- [Learning Versatile Convolution Filters for Efficient Visual Recognition](https://mlsanity.com/paper/2109.09310/) (2021)
- [GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMs](https://mlsanity.com/paper/2508.14302/) (2025)
- [Mixture-of-Rookies: Saving DNN Computations by Predicting ReLU Outputs](https://mlsanity.com/paper/2202.04990/) (2022)
- [Mobiprox: Supporting Dynamic Approximate Computing on Mobiles](https://mlsanity.com/paper/2303.11291/) (2023)

## 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.