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 551–600 of 1356 papers

TitleStatusHype
Structured Bayesian Compression for Deep Neural Networks Based on The Turbo-VBI Approach—0
HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers—0
A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques—0
Towards Optimal Compression: Joint Pruning and Quantization—0
Dual Relation Knowledge Distillation for Object DetectionCode1
On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence—0
Knowledge Distillation in Vision Transformers: A Critical Review—0
Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications—0
Knowledge Distillation on Graphs: A Survey—0
UPop: Unified and Progressive Pruning for Compressing Vision-Language TransformersCode1
AMD: Adaptive Masked Distillation for Object Detection—0
Improved knowledge distillation by utilizing backward pass knowledge in neural networks—0
Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI FeedbackCode0
HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks—0
HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble—0
SSDA: Secure Source-Free Domain AdaptationCode0
Tiny Updater: Towards Efficient Neural Network-Driven Software UpdatingCode0
ICD-Face: Intra-class Compactness Distillation for Face Recognition—0
Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis—0
One-Shot Model for Mixed-Precision Quantization—0
Distilling Focal Knowledge From Imperfect Expert for 3D Object DetectionCode0
Compression-Aware Video Super-ResolutionCode1
FlatENN: Train Flat for Enhanced Fault Tolerance of Quantized Deep Neural Networks—0
BD-KD: Balancing the Divergences for Online Knowledge Distillation—0
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
Spike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification taskCode0
FSCNN: A Fast Sparse Convolution Neural Network Inference System—0
Can We Find Strong Lottery Tickets in Generative Models?—0
Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework—0
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision TransformersCode1
Efficient Speech Representation Learning with Low-Bit Quantization—0
Error-aware Quantization through Noise Tempering—0
Leveraging Different Learning Styles for Improved Knowledge Distillation in Biomedical Imaging—0
FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street ViewsCode1
CSTAR: Towards Compact and STructured Deep Neural Networks with Adversarial Robustness—0
GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning—0
Compressing Cross-Lingual Multi-Task Models at Qualtrics—0
Compressing Volumetric Radiance Fields to 1 MBCode2
Discovering Dynamic Patterns from Spatiotemporal Data with Time-Varying Low-Rank AutoregressionCode1
Unbiased Knowledge Distillation for RecommendationCode1
Design and Prototyping Distributed CNN Inference Acceleration in Edge Computing—0
Sparse Probabilistic Circuits via Pruning and GrowingCode1
Learning Low-Rank Representations for Model Compression—0
Understanding and Improving Knowledge Distillation for Quantization-Aware Training of Large Transformer EncodersCode0
Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech TransformersCode0
Edge-MultiAI: Multi-Tenancy of Latency-Sensitive Deep Learning Applications on Edge—0
Understanding the Role of Mixup in Knowledge Distillation: An Empirical StudyCode0
XAI-BayesHAR: A novel Framework for Human Activity Recognition with Integrated Uncertainty and Shapely Values—0
Model Compression for DNN-based Speaker Verification Using Weight Quantization—0
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained TransformersCode7
Show:102550
← PrevPage 12 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