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 1101–1125 of 1356 papers

TitleStatusHype
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
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
GeneCAI: Genetic Evolution for Acquiring Compact AI—0
LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression—0
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
Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs—0
PCNN: Pattern-based Fine-Grained Regular Pruning towards Optimizing CNN Accelerators—0
Understanding and Improving Knowledge Distillation—0
Show:102550
← PrevPage 45 of 55Next →
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