Layer-compensated Pruning for Resource-constrained Convolutional Neural Networks
Explore this paper's citation graph
Summary
This work aims to improve the performance of resource-constrained filter pruning by merging two sub-problems commonly considered, i.e., how many filters to prune for each layer and which filters toPrune given a per-layer pruning budget, into a global filter ranking problem.
- Type
- preprint
- Published
- 2018-10-01
- Cited by
- 50
- References
- 39
- Access
- Open access
- OpenAlex
- https://openalex.org/W2893585013
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:52897447
Keywords
Computer science, Pruning, Residual neural network, Convolutional neural network, Enhanced Data Rates for GSM Evolution
References
- The Caltech-UCSD Birds-200-2011 Dataset
- ImageNet Large Scale Visual Recognition Challenge
- Reinforcement Learning: An Introduction
- Deep Residual Learning for Image Recognition
- Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
- Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
- Data-Driven Sparse Structure Selection for Deep Neural Networks
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
- CondenseNet: An Efficient DenseNet Using Learned Group Convolutions
- MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
- PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
- Faster gaze prediction with dense networks and Fisher pruning
- Regularized Evolution for Image Classifier Architecture Search
- ADC: Automated Deep Compression and Acceleration with Reinforcement Learning
- Adaptive Quantization of Neural Networks
- Compressing Neural Networks using the Variational Information Bottleneck
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension
- End-to-End Learning of Energy-Constrained Deep Neural Networks
- Accelerating Convolutional Networks via Global & Dynamic Filter Pruning
Cited by
- Rethinking the Value of Network Pruning
- Pruning neural networks: is it time to nip it in the bud?
- Hybrid Pruning: Thinner Sparse Networks for Fast Inference on Edge Devices
- ECC: Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
- A Framework for Fast and Efficient Neural Network Compression
- Meta Filter Pruning to Accelerate Deep Convolutional Neural Networks
- Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
- Data-Driven Neuron Allocation for Scale Aggregation Networks
- OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks
- MnnFast: A Fast and Scalable System Architecture for Memory-Augmented Neural Networks
- Parameterized Structured Pruning for Deep Neural Networks
- Differentiable Training for Hardware Efficient LightNNs
- Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization
- Efficient Neural Network Compression
- AutoML: A Survey of the State-of-the-Art
- ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
- Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
- LeanConvNets: Low-Cost Yet Effective Convolutional Neural Networks
- PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning
- Automating Deep Neural Network Model Selection for Edge Inference
Related papers
- Residual Network 모델의 특징에 관한 실증비교연구
- ResNet for Histopathologic Cancer Detection, the Deeper, the Better?
- Survey of Street Trees Pruning in Guangzhou Urban Green Space
- Effects of Different Pruning Methods on Seed Yield of Hybrid Tomato
- Road Network Traffic Data Prediction Using ResNet
- Multiway Pruning for Efficient Iceberg Cubing
- Vigour, pruning, and cropping in the grapevine (Vitis vinifera L.). II. Experiments on vigour, pruning and cropping.
- Effects of Pruning on the Health of Palms
- Study on the New Pruning Method and Technology of Poplar