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 151–200 of 1356 papers

TitleStatusHype
CrossKD: Cross-Head Knowledge Distillation for Object DetectionCode1
COMCAT: Towards Efficient Compression and Customization of Attention-Based Vision ModelsCode1
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN ExecutionCode1
LiMuSE: Lightweight Multi-modal Speaker ExtractionCode1
Class Attention Transfer Based Knowledge DistillationCode1
DarwinLM: Evolutionary Structured Pruning of Large Language ModelsCode1
Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated LearningCode1
Localize-and-Stitch: Efficient Model Merging via Sparse Task ArithmeticCode1
Communication-Computation Trade-Off in Resource-Constrained Edge InferenceCode1
A Unified Pruning Framework for Vision TransformersCode1
Merging Feed-Forward Sublayers for Compressed TransformersCode1
DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model GeneralizationCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer ProgrammingCode1
DE-RRD: A Knowledge Distillation Framework for Recommender SystemCode1
Densely Guided Knowledge Distillation using Multiple Teacher AssistantsCode1
Implicit Regularization via Neural Feature AlignmentCode1
Hyper-Compression: Model Compression via HyperfunctionCode1
Discrimination-aware Channel Pruning for Deep Neural NetworksCode1
Discrimination-aware Network Pruning for Deep Model CompressionCode1
Improve Object Detection with Feature-based Knowledge Distillation: Towards Accurate and Efficient DetectorsCode1
A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution RobustnessCode1
Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID DataCode1
Backdoor Attacks on Federated Learning with Lottery Ticket HypothesisCode1
DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and TransformersCode1
Distilling Object Detectors with Feature RichnessCode1
Basic Binary Convolution Unit for Binarized Image Restoration NetworkCode1
Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model CompressionCode1
Dual Relation Knowledge Distillation for Object DetectionCode1
Dynamic Channel Pruning: Feature Boosting and SuppressionCode1
Passport-aware Normalization for Deep Model ProtectionCode1
Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded DevicesCode1
EarlyBERT: Efficient BERT Training via Early-bird Lottery TicketsCode1
BERT-EMD: Many-to-Many Layer Mapping for BERT Compression with Earth Mover's DistanceCode1
BERT-of-Theseus: Compressing BERT by Progressive Module ReplacingCode1
Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and BetterCode1
CHEX: CHannel EXploration for CNN Model CompressionCode1
Progressive Network Grafting for Few-Shot Knowledge DistillationCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Bidirectional Distillation for Top-K Recommender SystemCode1
Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product OperatorsCode1
Faster and Lighter LLMs: A Survey on Current Challenges and Way ForwardCode1
Towards Compact Neural Networks via End-to-End Training: A Bayesian Tensor Approach with Automatic Rank DeterminationCode1
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic HashingCode1
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-PointCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
Initialization and Regularization of Factorized Neural LayersCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Accurate Retraining-free Pruning for Pretrained Encoder-based Language ModelsCode1
Memory-Efficient Backpropagation through Large Linear LayersCode1
Show:102550
← PrevPage 4 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