Runtime Neural Pruning
Explore this paper's citation graph
Summary
A Runtime Neural Pruning (RNP) framework which prunes the deep neural network dynamically at the runtime and preserves the full ability of the original network and conducts pruning according to the input image and current feature maps adaptively.
- Type
- article
- Published
- 2017-01-01
- Cited by
- 533
- References
- 46
- OpenAlex
- https://openalex.org/W2752037867
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:38486148
Keywords
Pruning, Computer science, Artificial neural network, Feature (linguistics), Convolutional neural network
References
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Phoneme probability estimation with dynamic sparsely connected artificial neural networks
- Reinforcement learning improves behaviour from evaluative feedback
- cuDNN: Efficient Primitives for Deep Learning
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments
- Auto-Sizing Neural Networks: With Applications to n-gram Language Models
- A convolutional neural network cascade for face detection
- Deep Convolutional Network Cascade for Facial Point Detection
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- DYNAMIC PROGRAMMING AND LAGRANGE MULTIPLIERS.
- Timely Object Recognition
- Accelerating Very Deep Convolutional Networks for Classification and Detection
- Gradient-based learning applied to document recognition
- Optimal Brain Damage
- ImageNet Large Scale Visual Recognition Challenge
- Markov Decision Processes: Discrete Stochastic Dynamic Programming
- Comparing Biases for Minimal Network Construction with Back-Propagation
- Second Order Derivatives for Network Pruning: Optimal Brain Surgeon
- Human-level control through deep reinforcement learning
Cited by
- Universal Deep Neural Network Compression
- ADC: Automated Deep Compression and Acceleration with Reinforcement Learning
- Compressing Neural Networks using the Variational Information Bottleneck
- Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds
- AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference
- Compression of Deep Convolutional Neural Networks under Joint Sparsity Constraints
- Channel Gating Neural Networks
- TAFE-Net: Task-Aware Feature Embeddings for Efficient Learning and Inference.
- Doubly Nested Network for Resource-Efficient Inference
- Spatial Correlation and Value Prediction in Convolutional Neural Networks
- Building a Robust Text Classifier on a Test-Time Budget
- Learning Low Precision Deep Neural Networks through Regularization
- How to Stop Off-the-Shelf Deep Neural Networks from Overthinking
- Dynamic Channel Pruning: Feature Boosting and Suppression
- Rethinking the Value of Network Pruning
- From Data to Knowledge: Deep Learning Model Compression, Transmission and Communication
- NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision
- Runtime Network Routing for Efficient Image Classification
- Balanced Sparsity for Efficient DNN Inference on GPU
- HAQ: Hardware-Aware Automated Quantization