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 1176–1200 of 1356 papers

TitleStatusHype
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 48 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