SOTAVerified

Model Compression

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.

Source: KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1051–1100 of 1356 papers

TitleStatusHype
ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification—0
Knowledge Distillation Meets Self-SupervisionCode1
Dynamic Model Pruning with Feedback—0
An Embedded Deep Learning Object Detection Model For Traffic In Asian Countries—0
Knowledge Distillation: A Survey—0
EDCompress: Energy-Aware Model Compression for Dataflows—0
AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles—0
An Overview of Neural Network Compression—0
Communication-Computation Trade-Off in Resource-Constrained Edge InferenceCode1
Multi-Dimensional Pruning: A Unified Framework for Model Compression—0
Discrete Model Compression With Resource Constraint for Deep Neural Networks—0
Online Knowledge Distillation via Collaborative LearningCode1
Weight Squeezing: Reparameterization for Compression and Fast Inference—0
CoDiNet: Path Distribution Modeling with Consistency and Diversity for Dynamic RoutingCode0
Exploiting Non-Linear Redundancy for Neural Model Compression—0
Position-based Scaled Gradient for Model Quantization and PruningCode1
TinyLSTMs: Efficient Neural Speech Enhancement for Hearing AidsCode1
VecQ: Minimal Loss DNN Model Compression With Vectorized Weight QuantizationCode0
MicroNet for Efficient Language ModelingCode1
A flexible, extensible software framework for model compression based on the LC algorithm—0
PENNI: Pruned Kernel Sharing for Efficient CNN InferenceCode0
Compressing Recurrent Neural Networks Using Hierarchical Tucker Tensor Decomposition—0
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey—0
SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation—0
Distilling Spikes: Knowledge Distillation in Spiking Neural Networks—0
WoodFisher: Efficient Second-Order Approximation for Neural Network CompressionCode1
Streamlining Tensor and Network Pruning in PyTorch—0
Robust testing of low-dimensional functions—0
PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices—0
Lottery Hypothesis based Unsupervised Pre-training for Model Compression in Federated Learning—0
Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation—0
Training with Quantization Noise for Extreme Model CompressionCode1
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New OutlooksCode2
KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflowCode1
GeneCAI: Genetic Evolution for Acquiring Compact AI—0
LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression—0
Orthant Based Proximal Stochastic Gradient Method for _1-Regularized OptimizationCode1
Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images—0
A Survey on Contextual Embeddings—0
A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework—0
Learning by Sampling and Compressing: Efficient Graph Representation Learning with Extremely Limited Annotations—0
Knowledge distillation via adaptive instance normalization—0
Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network—0
Adaptive Neural Connections for Sparsity Learning—0
An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation—0
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT—0
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural NetworksCode0
Residual Knowledge Distillation—0
Balancing Cost and Benefit with Tied-Multi Transformers—0
Show:102550
← PrevPage 22 of 28Next →
All datasetsImageNetQNLI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ADLIK-MO-ResNet50+W4A4Top-177.88—Unverified
2ADLIK-MO-ResNet50+W3A4Top-177.34—Unverified
3ResNet-18 + 4bit-1dim model compression using DKMTop-170.52—Unverified
4MobileNet-v1 + 4bit-1dim model compression using DKMTop-169.63—Unverified
5ResNet-18 + 2bit-1dim model compression using DKMTop-168.63—Unverified
6MobileNet-v1 + 2bit-1dim model compression using DKMTop-167.62—Unverified
7ResNet-18 + 4bit-4dim model compression using DKMTop-166.1—Unverified
8ResNet-18 + 2bit-2dim model compression using DKMTop-164.7—Unverified
9MobileNet-v1 + 4bit-4dim model compression using DKMTop-161.4—Unverified
10ResNet-18 + 1bit-1dim model compression using DKMTop-159.7—Unverified
#ModelMetricClaimedVerifiedStatus
1MobileBERT + 2bit-1dim model compression using DKMAccuracy82.13—Unverified
2MobileBERT + 1bit-1dim model compression using DKMAccuracy63.17—Unverified