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 201–250 of 1356 papers

TitleStatusHype
General Instance Distillation for Object DetectionCode1
Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural NetworksCode1
Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse NetworkCode1
Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement LearningCode1
An Empirical Study of CLIP for Text-based Person SearchCode1
HAWQV3: Dyadic Neural Network QuantizationCode1
MobileNMT: Enabling Translation in 15MB and 30msCode1
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt TuningCode1
HiNeRV: Video Compression with Hierarchical Encoding-based Neural RepresentationCode1
Light Multi-segment Activation for Model CompressionCode0
Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and AlgorithmsCode0
Comprehensive SNN Compression Using ADMM Optimization and Activity RegularizationCode0
Are Compressed Language Models Less Subgroup Robust?Code0
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured SparsificationCode0
Learning Intrinsic Sparse Structures within Long Short-Term MemoryCode0
Towards Efficient Model Compression via Learned Global RankingCode0
Learning Deep and Compact Models for Gesture RecognitionCode0
APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-DesignCode0
Learning Efficient Detector with Semi-supervised Adaptive DistillationCode0
Learning Compression from Limited Unlabeled DataCode0
Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroupCode0
Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated LearningCode0
Language Model Knowledge Distillation for Efficient Question Answering in SpanishCode0
Knowledge Distillation with Reptile Meta-Learning for Pretrained Language Model CompressionCode0
Knowledge Grafting of Large Language ModelsCode0
Knowledge Translation: A New Pathway for Model CompressionCode0
Application Specific Compression of Deep Learning ModelsCode0
Knowledge Distillation for Singing Voice DetectionCode0
Knowledge Distillation as Semiparametric InferenceCode0
Knowledge Distillation for End-to-End Person SearchCode0
JavaScript Convolutional Neural Networks for Keyword Spotting in the Browser: An Experimental AnalysisCode0
PruMUX: Augmenting Data Multiplexing with Model CompressionCode0
Learning Accurate Performance Predictors for Ultrafast Automated Model CompressionCode0
InDistill: Information flow-preserving knowledge distillation for model compressionCode0
Chemical transformer compression for accelerating both training and inference of molecular modelingCode0
Annealing Knowledge DistillationCode0
A Programmable Approach to Neural Network CompressionCode0
Information-Theoretic Understanding of Population Risk Improvement with Model CompressionCode0
Characterizing and Understanding the Behavior of Quantized Models for Reliable DeploymentCode0
Change Is the Only Constant: Dynamic LLM Slicing based on Layer RedundancyCode0
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMsCode0
Causal Explanation of Convolutional Neural NetworksCode0
CASP: Compression of Large Multimodal Models Based on Attention SparsityCode0
An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2Code0
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and MemoryCode0
HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge DistillationCode0
I3D: Transformer architectures with input-dependent dynamic depth for speech recognitionCode0
How does topology of neural architectures impact gradient propagation and model performance?Code0
Canonical convolutional neural networksCode0
RanDeS: Randomized Delta Superposition for Multi-Model CompressionCode0
Show:102550
← PrevPage 5 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