# LCNN: Lookup-based Convolutional Neural Network

arXiv: https://arxiv.org/abs/1611.06473 · HTML: https://mlsanity.com/paper/1611.06473/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2016.

## Built on by (most cited first, 11 of 11)

- [LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup](https://mlsanity.com/paper/2302.03213/) (2023)
- [An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio](https://mlsanity.com/paper/2208.09646/) (2022)
- [MixtureGrowth: Growing Neural Networks by Recombining Learned Parameters](https://mlsanity.com/paper/2311.04251/) (2023)
- [SUGAR: Efficient Subgraph-level Training via Resource-aware Graph Partitioning](https://mlsanity.com/paper/2202.00075/) (2022)
- [YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers](https://mlsanity.com/paper/2203.03794/) (2022)
- [Model Compression using Progressive Channel Pruning](https://mlsanity.com/paper/2507.04792/) (2025)
- [Accelerating Deep Learning Classification with Error-controlled Approximate-key Caching](https://mlsanity.com/paper/2112.06671/) (2021)
- [Deep Lookup Network](https://mlsanity.com/paper/2509.13662/) (2025)
- [PRANC: Pseudo RAndom Networks for Compacting deep models](https://mlsanity.com/paper/2206.08464/) (2022)
- [Learning to Compose SuperWeights for Neural Parameter Allocation Search](https://mlsanity.com/paper/2312.01274/) (2023)
- [Pruning Very Deep Neural Network Channels for Efficient Inference](https://mlsanity.com/paper/2211.08339/) (2022)

## Abstract (arXiv)

Porting state of the art deep learning algorithms to resource constrained compute platforms (e.g. VR, AR, wearables) is extremely challenging. We propose a fast, compact, and accurate model for convolutional neural networks that enables efficient learning and inference. We introduce LCNN, a lookup-based convolutional neural network that encodes convolutions by few lookups to a dictionary that is trained to cover the space of weights in CNNs. Training LCNN involves jointly learning a dictionary and a small set of linear combinations. The size of the dictionary naturally traces a spectrum of trade-offs between efficiency and accuracy. Our experimental results on ImageNet challenge show that LCNN can offer 3.2x speedup while achieving 55.1% top-1 accuracy using AlexNet architecture. Our fastest LCNN offers 37.6x speed up over AlexNet while maintaining 44.3% top-1 accuracy. LCNN not only offers dramatic speed ups at inference, but it also enables efficient training. In this paper, we show the benefits of LCNN in few-shot learning and few-iteration learning, two crucial aspects of on-device training of deep learning models.