Efficient DNN Paper List

• Neural Architecture Search: A Survey
• Efficient Progressive Neural Architecture Search
• Complementary Binary Quantization for Joint Multiple Indexing
• Efficient DNN Neuron Pruning by Minimizing Layer-wise Nonlinear Reconstruction Error
• Accelerating Convolutional Networks via Global and Dynamic Filter Pruning
• Progressive Blockwise Knowledge Distillation for Neural Network Acceleration
• Where to Prune: Using LSTM to Guide End-to-end Pruning
• Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
• Distilling the Knowledge in a Neural Network
• Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
• Variational Dropout Sparsifies Deep Neural Networks
• Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
• Learning Intrinsic Sparse Structures within Long Short-Term Memory
• PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning
• NISP: Pruning Networks using Neuron Importance Score Propagation
• Learning Global Additive Explanations for Neural Nets Using Model Distillation
• Regularized Evolution for Image Classifier Architecture Search
• Efficient Sparse-Winograd Convolutional Neural Networks
• Attention-Based Guided Structured Sparsity of Deep Neural Networks
• Born-Again Neural Networks
• A Neurobiological Evaluation Metric for Neural Network Model Search
• HAQ: Hardware-Aware Automated Quantization with Mixed Precision
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• Towards Federated Learning at Scale: System Design
• The State of Sparsity in Deep Neural Networks
• Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
• MFAS: Multimodal Fusion Architecture Search
• Luck Matters: Understanding Training Dynamics of Deep ReLU Networks
• Filter Grafting for Deep Neural Networks
• Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks
• Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration
• DropNet: Reducing Neural Network Complexity via Iterative Pruning
• Deep Neural Networks for Object Detection
• Coreset-Based Neural Network Compression
• A theory of learning from different domains
• "Learning-Compression" Algorithms for Neural Net Pruning
• Compressing Neural Networks with the Hashing Trick
• Context-aware Deep Feature Compression for High-speed Visual Tracking
• Contrastive Representation Distillation
• Low-rank Compression of Neural Nets: Learning the Rank of Each Layer
• ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
• Learning to generate chairs with convolutional neural networks
• Dynamic Model Pruning with Feedback
• Structured Multi-Hashing for Model Compression
• Ensemble Distribution Distillation
• Discrete Model Compression with Resource Constraint for Deep Neural Networks
• Multi-Dimensional Pruning: A Unified Framework for Model Compression
• Online Knowledge Distillation via Collaborative Learning
• The Knowledge Within: Methods for Data-Free Model Compression
• Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration
• Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing
• A Diversity-Penalizing Ensemble Training Method for Deep Learning
• Low-rank Compression of Neural Nets: Learning the Rank of Each Layer
• Knowledge Consistency between Neural Networks and Beyond
• Structured Compression by Weight Encryption for Unstructured Pruning and Quantization
• Few Sample Knowledge Distillation for Efficient Network Compression
• GAN Compression: Efficient Architectures for Interactive Conditional GANs
• Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression
• HRank: Filter Pruning using High-Rank Feature Map
• Neural Network Pruning with Residual-Connections and Limited-Data
• ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions
• Discrimination-aware Channel Pruning for Deep Neural Networks
• Frequency-Domain Dynamic Pruning for Convolutional Neural Networks
• Variational Mutual Information Distillation for Transfer Learning
• Bayesian Dark Knowledge
• CNNpack: Packing Convolutional Neural Networks in the Frequency Domain
• Sobolev Training for Neural Networks
• Learning the Structure of Deep Architectures Using l₁ Regularization
• Heterogeneous Knowledge Distillation using Information Flow Modeling
• Picking Winning Tickets Before Training by Preserving Gradient Flow
• SNAS: Stochastic Neural Architecture Search
• A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
• Towards Evolutionary Compression
• APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
• MineGAN: effective knowledge transfer from GANs to target domains with few images
• Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model
• Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach
• Distilling Knowledge from Graph Convolutional Networks
• Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN
• Distilling Cross-Task Knowledge via Relationship Matching
• A Gift from Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning
• Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
• Revisiting Knowledge Distillation via Label Smoothing Regularization
• Regularizing Class-wise Predictions via Self-knowledge Distillation
• Data-Driven Sparse Structure Selection for Deep Neural Networks
• Less is More: Towards Compact CNNs
• Towards Effective Low-bitwidth Convolutional Neural Networks