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 801–850 of 1356 papers

TitleStatusHype
The Effect of Model Compression on Fairness in Facial Expression Recognition—0
The Impact of Quantization and Pruning on Deep Reinforcement Learning Models—0
The Knowledge Within: Methods for Data-Free Model Compression—0
The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?—0
Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks—0
The Potential of AutoML for Recommender Systems—0
Three Dimensional Convolutional Neural Network Pruning with Regularization-Based Method—0
Tight Compression: Compressing CNN Through Fine-Grained Pruning and Weight Permutation for Efficient Implementation—0
Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning—0
Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation—0
TinyM^2Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment—0
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation—0
To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference—0
To Know Where We Are: Vision-Based Positioning in Outdoor Environments—0
Topology Distillation for Recommender System—0
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation—0
Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM—0
Toward Real-World Voice Disorder Classification—0
Towards Accurate Post-Training Quantization for Vision Transformer—0
Towards a tailored mixed-precision sub-8-bit quantization scheme for Gated Recurrent Units using Genetic Algorithms—0
Towards Better Parameter-Efficient Fine-Tuning for Large Language Models: A Position Paper—0
Towards Building a Real Time Mobile Device Bird Counting System Through Synthetic Data Training and Model Compression—0
Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation—0
Towards efficient deep autoencoders for multivariate time series anomaly detection—0
Towards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning—0
Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization—0
Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework—0
Towards Higher Ranks via Adversarial Weight Pruning—0
Towards Modality Transferable Visual Information Representation with Optimal Model Compression—0
Towards Optimal Compression: Joint Pruning and Quantization—0
Towards Superior Quantization Accuracy: A Layer-sensitive Approach—0
Do we need Label Regularization to Fine-tune Pre-trained Language Models?—0
Towards Zero-Shot Knowledge Distillation for Natural Language Processing—0
Train Flat, Then Compress: Sharpness-Aware Minimization Learns More Compressible Models—0
Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization—0
T-RECX: Tiny-Resource Efficient Convolutional neural networks with early-eXit—0
TrimLLM: Progressive Layer Dropping for Domain-Specific LLMs—0
Trimming Down Large Spiking Vision Transformers via Heterogeneous Quantization Search—0
Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy—0
Tuning Algorithms and Generators for Efficient Edge Inference—0
TutorNet: Towards Flexible Knowledge Distillation for End-to-End Speech Recognition—0
TwinDNN: A Tale of Two Deep Neural Networks—0
Two-Bit Networks for Deep Learning on Resource-Constrained Embedded Devices—0
Two is Better than One: Efficient Ensemble Defense for Robust and Compact Models—0
Two-Pass End-to-End ASR Model Compression—0
Two-Step Knowledge Distillation for Tiny Speech Enhancement—0
UDC: Unified DNAS for Compressible TinyML Models—0
Understanding and Improving Knowledge Distillation—0
Understanding LLMs: A Comprehensive Overview from Training to Inference—0
Unleashing Channel Potential: Space-Frequency Selection Convolution for SAR Object Detection—0
Show:102550
← PrevPage 17 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