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
Improved Knowledge Distillation via Full Kernel Matrix TransferCode0
Pea-KD: Parameter-efficient and accurate Knowledge Distillation—0
Conditional Automated Channel Pruning for Deep Neural Networks—0
MSP: An FPGA-Specific Mixed-Scheme, Multi-Precision Deep Neural Network Quantization Framework—0
A Progressive Sub-Network Searching Framework for Dynamic Inference—0
Binary Classification as a Phase Separation ProcessCode0
Compression-aware Continual Learning using Singular Value DecompositionCode0
Layer-specific Optimization for Mixed Data Flow with Mixed Precision in FPGA Design for CNN-based Object Detectors—0
A Partial Regularization Method for Network Compression—0
Against Membership Inference Attack: Pruning is All You Need—0
One Weight Bitwidth to Rule Them All—0
Data-Independent Structured Pruning of Neural Networks via Coresets—0
Cascaded channel pruning using hierarchical self-distillation—0
Towards Modality Transferable Visual Information Representation with Optimal Model Compression—0
Adaptive Learning of Tensor Network Structures—0
Iterative Compression of End-to-End ASR Model using AutoML—0
Structured Convolutions for Efficient Neural Network Design—0
TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition—0
Differentiable Feature Aggregation Search for Knowledge Distillation—0
Compressing Deep Neural Networks via Layer Fusion—0
ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks—0
RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices—0
FTRANS: Energy-Efficient Acceleration of Transformers using FPGA—0
Representation Transfer by Optimal Transport—0
Learning to Prune Deep Neural Networks via Reinforcement Learning—0
Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks—0
Self-Supervised GAN CompressionCode0
Knowledge Distillation Beyond Model Compression—0
Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture—0
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks—0
Exploring the Limits of Simple Learners in Knowledge Distillation for Document Classification with DocBERT—0
On the Demystification of Knowledge Distillation: A Residual Network Perspective—0
PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration—0
Additive Tree-Structured Covariance Function for Conditional Parameter Spaces in Bayesian Optimization—0
ResOT: Resource-Efficient Oblique Trees for Neural Signal Classification—0
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
Discrete Model Compression With Resource Constraint for Deep Neural Networks—0
Multi-Dimensional Pruning: A Unified Framework for Model Compression—0
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
VecQ: Minimal Loss DNN Model Compression With Vectorized Weight QuantizationCode0
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
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