# Constructing Fast Network through Deconstruction of Convolution

arXiv: https://arxiv.org/abs/1806.07370 · HTML: https://mlsanity.com/paper/1806.07370/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 24 of 24)

- [A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift](https://mlsanity.com/paper/2206.10810/) (2022)
- [Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities](https://mlsanity.com/paper/2210.06640/) (2022)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [When Shift Operation Meets Vision Transformer: An Extremely Simple Alternative to Attention Mechanism](https://mlsanity.com/paper/2201.10801/) (2022)
- [A survey on Variational Autoencoders from a GreenAI perspective](https://mlsanity.com/paper/2103.01071/) (2021)
- [GhostNets on Heterogeneous Devices via Cheap Operations](https://mlsanity.com/paper/2201.03297/) (2022)
- [Efficiency is Not Enough: A Critical Perspective of Environmentally Sustainable AI](https://mlsanity.com/paper/2309.02065/) (2023)
- [EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Search](https://mlsanity.com/paper/2210.06015/) (2022)
- [Dissecting FLOPs along input dimensions for GreenAI cost estimations](https://mlsanity.com/paper/2107.11949/) (2021)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation](https://mlsanity.com/paper/2403.03344/) (2024)
- [Fully 1×1 Convolutional Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2307.16140/) (2023)
- [TS-SNN: Temporal Shift Module for Spiking Neural Networks](https://mlsanity.com/paper/2505.04165/) (2025)
- [HAA4D: Few-Shot Human Atomic Action Recognition via 3D Spatio-Temporal Skeletal Alignment](https://mlsanity.com/paper/2202.07308/) (2022)
- [ShiftwiseConv: Small Convolutional Kernel with Large Kernel Effect](https://mlsanity.com/paper/2401.12736/) (2024)
- [Improving Generalization of Batch Whitening by Convolutional Unit Optimization](https://mlsanity.com/paper/2108.10629/) (2021)
- [Learning Versatile Convolution Filters for Efficient Visual Recognition](https://mlsanity.com/paper/2109.09310/) (2021)
- [Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIs](https://mlsanity.com/paper/2305.02440/) (2023)
- [BMRS: Bayesian Model Reduction for Structured Pruning](https://mlsanity.com/paper/2406.01345/) (2024)
- [Evaluation of Convolution Primitives for Embedded Neural Networks on 32-bit Microcontrollers](https://mlsanity.com/paper/2303.10702/) (2023)
- [Compact Neural Networks via Stacking Designed Basic Units](https://mlsanity.com/paper/2205.01508/) (2022)
- [Efficient Online Processing with Deep Neural Networks](https://mlsanity.com/paper/2306.13474/) (2023)
- [Mixer is more than just a model](https://mlsanity.com/paper/2402.18007/) (2024)
- [Parameter-Efficient 3D Segmentation of Liver and Liver tumors: Depthwise factorization Scales Better Than Dense Convolution with Spatial Dimensionality](https://mlsanity.com/paper/2609.33077/) (2026)

## Abstract (arXiv)

Convolutional neural networks have achieved great success in various vision tasks; however, they incur heavy resource costs. By using deeper and wider networks, network accuracy can be improved rapidly. However, in an environment with limited resources (e.g., mobile applications), heavy networks may not be usable. This study shows that naive convolution can be deconstructed into a shift operation and pointwise convolution. To cope with various convolutions, we propose a new shift operation called active shift layer (ASL) that formulates the amount of shift as a learnable function with shift parameters. This new layer can be optimized end-to-end through backpropagation and it can provide optimal shift values. Finally, we apply this layer to a light and fast network that surpasses existing state-of-the-art networks.