# TabConv: Low-Computation CNN Inference via Table Lookups

arXiv: https://arxiv.org/abs/2404.05872 · HTML: https://mlsanity.com/paper/2404.05872/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 48 references that are in the map.
- First posted on arXiv 8 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation](https://mlsanity.com/paper/1909.11065/) (2019)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [cuDNN: Efficient Primitives for Deep Learning](https://mlsanity.com/paper/1410.0759/) (2014)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [Fast Algorithms for Convolutional Neural Networks](https://mlsanity.com/paper/1509.09308/) (2015)
- [DeepShift: Towards Multiplication-Less Neural Networks](https://mlsanity.com/paper/1905.13298/) (2019)
- [Optimal approximate matrix product in terms of stable rank](https://mlsanity.com/paper/1507.02268/) (2015)
- [Parallel Multi Channel Convolution using General Matrix Multiplication](https://mlsanity.com/paper/1704.04428/) (2017)
- [Multiplying Matrices Without Multiplying](https://mlsanity.com/paper/2106.10860/) (2021)
- [Accelerating CNN inference on FPGAs: A Survey](https://mlsanity.com/paper/1806.01683/) (2018)
- [The Effects of Approximate Multiplication on Convolutional Neural Networks](https://mlsanity.com/paper/2007.10500/) (2020)
- [Fine-Grained Address Segmentation for Attention-Based Variable-Degree Prefetching](https://mlsanity.com/paper/2205.02269/) (2022)
- [PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models](https://mlsanity.com/paper/2402.13441/) (2024)
- [Efficient distributed algorithms for Convolutional Neural Networks](https://mlsanity.com/paper/2105.13480/) (2021)

## Built on by (most cited first, 1 of 1)

- [Mitigating scalability challenges in LUT-based neural networks via pruning optimisations](https://mlsanity.com/paper/2407.02362/) (2024)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have demonstrated remarkable ability throughout the field of computer vision. However, CNN inference requires a large number of arithmetic operations, making them expensive to deploy in hardware. Current approaches alleviate this issue by developing hardware-supported, algorithmic processes to simplify spatial convolution functions. However, these methods still heavily rely on matrix multiplication, leading to significant computational overhead. To bridge the gap between hardware, algorithmic acceleration, and approximate matrix multiplication, we propose TabConv, a novel, table-based approximation for convolution to significantly reduce arithmetic operations during inference. Additionally, we introduce a priority masking technique based on cosine similarity to select layers for table-based approximation, thereby maintaining the model performance. We evaluate our approach on popular CNNs: ResNet-18, ResNet-34, and NetworkInNetwork (NIN). TabConv preserves over 93% of the original model's performance while reducing arithmetic operations by 36.5%, 25.8%, and 99.4% for ResNet-18 on CIFAR-10, CIFAR-100, and MNIST, respectively, 35.6% and 99.3% for ResNet-34 on CIFAR-10 and MNIST, and 98.9% for NIN on MNIST, achieving low-computation inference.