About
Model Compression is an actively pursued area of research over the last few years with the goal of deploying state-of-the-art deep networks in low-power and resource limited devices without significant drop in accuracy. Parameter pruning, low-rank factorization and weight quantization are some of the proposed methods to compress the size of deep networks.
Benchmarks
Subtasks
Datasets
Greatest papers with code
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
ICLR 2020
• google-research/bert
• 
Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training.
KNOWLEDGE DISTILLATION LANGUAGE MODELLING MODEL COMPRESSION SENTIMENT ANALYSIS
What Do Compressed Deep Neural Networks Forget?
• google-research/google-research
•
However, this measure of performance conceals significant differences in how different classes and images are impacted by model compression techniques.
FAIRNESS INTERPRETABILITY TECHNIQUES FOR DEEP LEARNING MODEL COMPRESSION NETWORK PRUNING OUTLIER DETECTION QUANTIZATION
The State of Sparsity in Deep Neural Networks
• google-research/google-research
•
We rigorously evaluate three state-of-the-art techniques for inducing sparsity in deep neural networks on two large-scale learning tasks: Transformer trained on WMT 2014 English-to-German, and ResNet-50 trained on ImageNet.
Training with Quantization Noise for Extreme Model Compression
A standard solution is to train networks with Quantization Aware Training, where the weights are quantized during training and the gradients approximated with the Straight-Through Estimator.
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
• pytorch/vision
• 
(2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car.
Model compression via distillation and quantization
ICLR 2018
• NervanaSystems/distiller
•
Deep neural networks (DNNs) continue to make significant advances, solving tasks from image classification to translation or reinforcement learning.
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
ECCV 2018
• NervanaSystems/distiller
•
Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets.
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks
• FLHonker/Awesome-Knowledge-Distillation
•
To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another.
Contrastive Representation Distillation
ICLR 2020
• HobbitLong/RepDistiller
•
We demonstrate that this objective ignores important structural knowledge of the teacher network.
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
NeurIPS 2019
• ShawnDing1994/ACNet
•
Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices.