Blog

Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization Generative Low-bitwidth Data Free Quantization Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian Process Post-Training Piecewise Linear Quantization for Deep Neural Networks Task-Aware Quantization Network for JPEG Image Compresssion HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs Deep ..

EagleEye: Fast Sub-network Evaluation for Efficient Neural Network Pruning (oral) DAS: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation DHP: Differentiable Meta Pruning via HyperNetworks Meta-Learning with Network Pruning DN-NAS: Data Adapted Pruning for Efficient Neural Architecture Search Differentiable Joint Pruning and Quantization for Hardware Efficiency Accelerating C..

Robust Quantization: One Model to Rule Them All Adaptive Gradient Quantization for Data-Parallel SGD Position-based Scaled Gradient for Model Quantization and Sparse Training AMQ: Automatic Mixed-precision Quantization Based on Hessian Trace FleXOR: Trainable Fractional Quantization Bayesian Bits: Unifying Quantization and Pruning Universally Quantized Neural Compression Hierarchical Quantized A..

Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot Scientific Control for Reliable Neural Network Pruning Pruning Filter in Filter Neuron-level Structured Pruning using Polarization Regularizer Directional Pruning of Deep Neural Networks Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning Movement Pruning: Adaptive Sparsity by Fine-Tuni..

Adversarial Neural Pruning with Latent Vulnerability Supperession (KAIST) Operate-Aware Soft Channel Pruning using Differentiable Masks (SNU) Network Pruning by Greedy Subnetwork Selection DropNet: Reducing Neural Network Complexity via Iterative Pruning Proving the Lottery Ticket Hypothesis: Pruning is All You Need Towards Accuarte Post-traing Network Quantization via Bit-Split and Stitching On..

Neural Network Pruning With Residual-Connection and Limited-Data Multi-Dimensional Pruning: A Unifed Frameworkd for Model Compression HRank: Filter Pruning Using High-Rank Feature Map DMCP: Differentaible Markov Channel Pruning for Neural Networks Structured Compression by Weight Encryption for Unstructured Pruning and Quantization Learning Filter Pruning Criteria for Deep Convolutional Neural N..

MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning Accelerate CNN via Recursive Bayesian Pruning Adversarial Robustness vs. Model Compression on, or Both?

Collaborative Channel Pruning for Deep Networks Approximated Oracle Filter Pruning for Destructive CNN Width Optimization EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis LIT: Learned Intermediate Representation Training for Model Compression

Reborn Filters: Pruning Convolutional Neural Networks with Limited Data Learning Agent Communication under Limited Bandwidth by Message Pruning Dynamic Network Pruning with Interpretable Layerwise Channel Selection Real-Time Object Tracking via Meta-Learning: Efficient Model Adaptation and One-Shot Channel Pruning PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Exec..

One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation Lookahead: A Far-sighted Alternative of Magnitude-based Pruning Dynamic Model Pruning with Feedback Provable Filter Pruning for Efficient Neural Networks Data-Independent Neural Pruning via Coresets Comparing Fine-tuning and Rewinding in Neural Network Pruning (oral) A Signal Propagation Perspective for Pruning Neural ..