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 1151–1200 of 1356 papers

TitleStatusHype
Small Language Models: Architectures, Techniques, Evaluation, Problems and Future Adaptation—0
Small Object Detection Based on Modified FSSD and Model Compression—0
Smart Environmental Monitoring of Marine Pollution using Edge AI—0
SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation—0
Smooth Model Compression without Fine-Tuning—0
CrAFT: Compression-Aware Fine-Tuning for Efficient Visual Task Adaptation—0
Soft Labeling Affects Out-of-Distribution Detection of Deep Neural Networks—0
Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge—0
SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching—0
Sparse Deep Learning for Time Series Data: Theory and Applications—0
AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles—0
Sparse Unbalanced GAN Training with In-Time Over-Parameterization—0
Spatio-Temporal Pruning and Quantization for Low-latency Spiking Neural Networks—0
Activation Sparsity Opportunities for Compressing General Large Language Models—0
Compressible Spectral Mixture Kernels with Sparse Dependency Structures for Gaussian Processes—0
Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error—0
Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models—0
Comprehensive Survey of Model Compression and Speed up for Vision Transformers—0
Speeding up Convolutional Neural Networks with Low Rank Expansions—0
Compressed models are NOT miniature versions of large models—0
Speeding Up Image Classifiers with Little Companions—0
USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models—0
Compressing Cross-Lingual Multi-Task Models at Qualtrics—0
Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters—0
Compressing Deep Neural Networks via Layer Fusion—0
Compositionality Unlocks Deep Interpretable Models—0
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT—0
Compressing Low Precision Deep Neural Networks Using Sparsity-Induced Regularization in Ternary Networks—0
Compressing Pre-trained Language Models by Matrix Decomposition—0
Compressing Recurrent Neural Networks for FPGA-accelerated Implementation in Fluorescence Lifetime Imaging—0
Compressing Recurrent Neural Networks Using Hierarchical Tucker Tensor Decomposition—0
Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer—0
Sponge Attacks on Sensing AI: Energy-Latency Vulnerabilities and Defense via Model Pruning—0
CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting—0
Compression and Localization in Reinforcement Learning for ATARI Games—0
Activation Map Adaptation for Effective Knowledge Distillation—0
Complexity-Driven CNN Compression for Resource-constrained Edge AI—0
Compression for Better: A General and Stable Lossless Compression Framework—0
Compression Laws for Large Language Models—0
Compression of Deep Neural Networks by combining pruning and low rank decomposition—0
Compression of Deep Neural Networks for Image Instance Retrieval—0
Compression of Generative Pre-trained Language Models via Quantization—0
Compacting Deep Neural Networks for Internet of Things: Methods and Applications—0
Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt—0
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead—0
Computation-efficient Deep Learning for Computer Vision: A Survey—0
CompactifAI: Extreme Compression of Large Language Models using Quantum-Inspired Tensor Networks—0
Activation Density based Mixed-Precision Quantization for Energy Efficient Neural Networks—0
ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval—0
Conditional Automated Channel Pruning for Deep Neural Networks—0
Show:102550
← PrevPage 24 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