Browse > Methodology > Model Compression

Model Compression

21 papers with code ยท Methodology

State-of-the-art leaderboards

You can find evaluation results in the subtasks. You can also submitting evaluation metrics for this task.

Latest papers without code

Joint Pruning on Activations and Weights for Efficient Neural Networks

19 Jun 2019

By distinguishing and taking on the different significance of neuron responses and connections during learning, the generated network, namely JPnet, optimizes the sparsity of activations and weights for improving execution efficiency.

MODEL COMPRESSION

Model Compression by Entropy Penalized Reparameterization

15 Jun 2019

We describe an end-to-end neural network weight compression approach that draws inspiration from recent latent-variable data compression methods.

MODEL COMPRESSION

Reconciling Utility and Membership Privacy via Knowledge Distillation

15 Jun 2019

In this work, we present a new defense against membership inference attacks that preserves the utility of the target machine learning models significantly better than prior defenses.

INFERENCE ATTACK MODEL COMPRESSION

Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining

10 Jun 2019

Our key idea is to introduce a priority term that identifies the importance of a layer; we can select unimportant layers according to the priority and erase them after the training.

MODEL COMPRESSION

Deep Face Recognition Model Compression via Knowledge Transfer and Distillation

3 Jun 2019

However, deploying such high performing models to resource constraint devices or real-time applications is challenging.

FACE RECOGNITION MODEL COMPRESSION TRANSFER LEARNING

Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression

CVPR 2019

The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.

MODEL COMPRESSION

Compressing Convolutional Neural Networks via Factorized Convolutional Filters

CVPR 2019

The workflow of a traditional pruning consists of three sequential stages: pre-training the original model, selecting the pre-trained filters via ranking according to a manually designed criterion (e. g., the norm of filters), and learning the remained filters via fine-tuning.

MODEL COMPRESSION

Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1

31 May 2019

The training of deep neural networks (DNNs) requires intensive resources both for computation and for storage performance.

IMAGE CLASSIFICATION MODEL COMPRESSION OBJECT DETECTION

HadaNets: Flexible Quantization Strategies for Neural Networks

26 May 2019

On-board processing elements on UAVs are currently inadequate for training and inference of Deep Neural Networks.

MODEL COMPRESSION QUANTIZATION