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 1151–1200 of 1356 papers

TitleStatusHype
Graph Pruning for Model Compression—0
Few Shot Network Compression via Cross DistillationCode0
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks—0
On the Discrepancy between the Theoretical Analysis and Practical Implementations of Compressed Communication for Distributed Deep LearningCode0
Distributed Low Precision Training Without Mixed Precision—0
ASCAI: Adaptive Sampling for acquiring Compact AI—0
Data Efficient Stagewise Knowledge DistillationCode0
What Do Compressed Deep Neural Networks Forget?Code0
A Computing Kernel for Network Binarization on PyTorchCode0
SubCharacter Chinese-English Neural Machine Translation with Wubi encoding—0
Localization-aware Channel Pruning for Object Detection—0
A Programmable Approach to Neural Network CompressionCode0
Comprehensive SNN Compression Using ADMM Optimization and Activity RegularizationCode0
Locality-Sensitive Hashing for f-Divergences: Mutual Information Loss and Beyond—0
Cross-Channel Intragroup Sparsity Neural Network—0
LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution—0
Model Compression with Two-stage Multi-teacher Knowledge Distillation for Web Question Answering System—0
Structured Pruning of a BERT-based Question Answering Model—0
Model Fusion via Optimal TransportCode0
Differentiable Sparsification for Deep Neural Networks—0
Deep Neural Network Compression for Image Classification and Object DetectionCode0
How does topology influence gradient propagation and model performance of deep networks with DenseNet-type skip connections?Code0
Adversarial Robustness vs. Model Compression, or Both?Code0
REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs—0
Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning—0
Extremely Small BERT Models from Mixed-Vocabulary Training—0
Atomic Compression Networks—0
Network Pruning for Low-Rank Binary Index—0
GQ-Net: Training Quantization-Friendly Deep Networks—0
Decoupling Weight Regularization from Batch Size for Model Compression—0
Balancing Specialization, Generalization, and Compression for Detection and Tracking—0
Class-dependent Compression of Deep Neural NetworksCode0
Differentiable Mask for Pruning Convolutional and Recurrent Networks—0
PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices—0
LIT: Learned Intermediate Representation Training for Model CompressionCode0
Knowledge Distillation for End-to-End Person SearchCode0
Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation—0
On the Effectiveness of Low-Rank Matrix Factorization for LSTM Model Compression—0
Patient Knowledge Distillation for BERT Model CompressionCode0
MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors—0
Einconv: Exploring Unexplored Tensor Network Decompositions for Convolutional Neural NetworksCode0
Tuning Algorithms and Generators for Efficient Edge Inference—0
Memory- and Communication-Aware Model Compression for Distributed Deep Learning Inference on IoT—0
Real-Time Correlation Tracking via Joint Model Compression and TransferCode0
Light Multi-segment Activation for Model CompressionCode0
Neural Epitome Search for Architecture-Agnostic Network Compression—0
Data-Independent Neural Pruning via Coresets—0
ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning—0
AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates—0
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?—0
Show:102550
← PrevPage 24 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