Deep Lookup Network
Not on the map. Why?
Abstract (arXiv)
Convolutional neural networks are constructed with massive operations with different types and are highly computationally intensive. Among these operations, multiplication operation is higher in computational complexity and usually requires {more} energy consumption with longer inference time than other operations, which hinders the deployment of convolutional neural networks on mobile devices. In many resource-limited edge devices, complicated operations can be calculated via lookup tables to reduce computational cost. Motivated by this, in this paper, we introduce a generic and efficient lookup operation which can be used as a basic operation for the construction of neural networks. Instead of calculating the multiplication of weights and activation values, simple yet efficient lookup operations are adopted to compute their responses. To enable end-to-end optimization of the lookup operation, we construct the lookup tables in a differentiable manner and propose several training strategies to promote their convergence. By replacing computationally expensive multiplication operations with our lookup operations, we develop lookup networks for the image classification, image super-resolution, and point cloud classification tasks. It is demonstrated that our lookup networks can benefit from the lookup operations to achieve higher efficiency in terms of energy consumption and inference speed while maintaining competitive performance to vanilla convolutional networks. Extensive experiments show that our lookup networks produce state-of-the-art performance on different tasks (both classification and regression tasks) and different data types (both images and point clouds).
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 67 of its 94 references that are in the map. First posted on arXiv 17 Sep 2025.
Builds on
67 of 94 references.
References · 67
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2017Mask R-CNNcited by 7,277
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
38 more
- 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
- 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
- 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
- 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
- 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
- 2019Learned Step Size Quantizationcited by 628
- 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
- 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
- 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
- 2018PACT: Parameterized Clipping Activation for Quantized Neural Networkscited by 467
- 2019GhostNet: More Features from Cheap Operationscited by 410
- 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 367
- 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 315
- 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
- 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 274
- 2015Tensorizing Neural Networkscited by 250
- 2019Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networkscited by 238
- 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 235
- 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 217
- 2016A Decomposable Attention Model for Natural Language Inferencecited by 215
- 2016Trained Ternary Quantizationcited by 208
- 2018Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Losscited by 160
- 2019Quantization Networkscited by 153
- 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
- 2017Towards Accurate Binary Convolutional Neural Networkcited by 149
- 2019Towards Optimal Structured CNN Pruning via Generative Adversarial Learningcited by 146
- 2020Knowledge Distillation Meets Self-Supervisioncited by 142
- 2021Group Fisher Pruning for Practical Network Compressioncited by 131
- 2018Dynamic Channel Pruning: Feature Boosting and Suppressioncited by 129
- 2017Deep Learning with Low Precision by Half-wave Gaussian Quantizationcited by 117
- 2017Soft Weight-Sharing for Neural Network Compressioncited by 99
- 2017Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutionscited by 93
- 2019AdderNet: Do We Really Need Multiplications in Deep Learning?cited by 82
- 2021CHIP: CHannel Independence-based Pruning for Compact Neural Networkscited by 78
- 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
50 most cited of 67 All 67 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.