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 201–225 of 1356 papers

TitleStatusHype
Sparse Probabilistic Circuits via Pruning and GrowingCode1
Faster and Lighter LLMs: A Survey on Current Challenges and Way ForwardCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
An Empirical Study of CLIP for Text-based Person SearchCode1
FedUKD: Federated UNet Model with Knowledge Distillation for Land Use Classification from Satellite and Street ViewsCode1
Communication-Efficient Federated Learning through Adaptive Weight Clustering and Server-Side DistillationCode1
Multi-level Knowledge Distillation via Knowledge Alignment and CorrelationCode1
RepQ-ViT: Scale Reparameterization for Post-Training Quantization of Vision TransformersCode1
Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and AlgorithmsCode0
Is Modularity Transferable? A Case Study through the Lens of Knowledge DistillationCode0
Are Compressed Language Models Less Subgroup Robust?Code0
Information-Theoretic Understanding of Population Risk Improvement with Model CompressionCode0
Iterative Filter Pruning for Concatenation-based CNN ArchitecturesCode0
APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-DesignCode0
InDistill: Information flow-preserving knowledge distillation for model compressionCode0
JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental AnalysisCode0
A Programmable Approach to Neural Network CompressionCode0
Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated LearningCode0
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMsCode0
I3D: Transformer architectures with input-dependent dynamic depth for speech recognitionCode0
Image Classification with CondenseNeXt for ARM-Based Computing PlatformsCode0
Application Specific Compression of Deep Learning ModelsCode0
HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model CompressionCode0
HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge DistillationCode0
Show:102550
← PrevPage 9 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