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 1251–1300 of 1356 papers

TitleStatusHype
AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategyCode0
Differentially Private Knowledge Distillation via Synthetic Text GenerationCode0
SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCamCode0
Exploring Unexplored Tensor Network Decompositions for Convolutional Neural NetworksCode0
Patient Knowledge Distillation for BERT Model CompressionCode0
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI ScaleCode0
Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software DeploymentCode0
PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early ExitingCode0
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software DeploymentCode0
MiniDisc: Minimal Distillation Schedule for Language Model CompressionCode0
Chemical transformer compression for accelerating both training and inference of molecular modelingCode0
A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNsCode0
Training dynamic models using early exits for automatic speech recognition on resource-constrained devicesCode0
PENNI: Pruned Kernel Sharing for Efficient CNN InferenceCode0
subMFL: Compatiple subModel Generation for Federated Learning in Device Heterogenous EnvironmentCode0
Perforated Backpropagation: A Neuroscience Inspired Extension to Artificial Neural NetworksCode0
Exploring Gradient Flow Based Saliency for DNN Model CompressionCode0
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model CompressionCode0
LXMERT Model Compression for Visual Question AnsweringCode0
Deep Neural Network Compression for Image Classification and Object DetectionCode0
Tiny Updater: Towards Efficient Neural Network-Driven Software UpdatingCode0
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMsCode0
Aligning Logits Generatively for Principled Black-Box Knowledge DistillationCode0
Attacking Compressed Vision TransformersCode0
Exploiting Kernel Sparsity and Entropy for Interpretable CNN CompressionCode0
Explicit-NeRF-QA: A Quality Assessment Database for Explicit NeRF Model CompressionCode0
Characterizing and Understanding the Behavior of Quantized Models for Reliable DeploymentCode0
Physics Inspired Criterion for Pruning-Quantization Joint LearningCode0
Adversarial Robustness vs Model Compression, or Both?Code0
Deep Model Compression Also Helps Models Capture AmbiguityCode0
Play and Prune: Adaptive Filter Pruning for Deep Model CompressionCode0
PocketFlow: An Automated Framework for Compressing and Accelerating Deep Neural NetworksCode0
MedDet: Generative Adversarial Distillation for Efficient Cervical Disc Herniation DetectionCode0
DeepFont: Identify Your Font from An ImageCode0
Augmenting Deep Classifiers with Polynomial Neural NetworksCode0
Exact Backpropagation in Binary Weighted Networks with Group Weight TransformationsCode0
Pool of Experts: Realtime Querying Specialized Knowledge in Massive Neural NetworksCode0
Training Thinner and Deeper Neural Networks: Jumpstart RegularizationCode0
Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution AlignmentCode0
DeepCompress-ViT: Rethinking Model Compression to Enhance Efficiency of Vision Transformers at the EdgeCode0
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical PerspectiveCode0
What Do Compressed Deep Neural Networks Forget?Code0
MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face ImagesCode0
Empirical Evaluation of Deep Learning Model Compression Techniques on the WaveNet VocoderCode0
Advances in Small-Footprint Keyword Spotting: A Comprehensive Review of Efficient Models and AlgorithmsCode0
Selective Pre-training for Private Fine-tuningCode0
Asymmetric Masked Distillation for Pre-Training Small Foundation ModelsCode0
Minimizing PLM-Based Few-Shot Intent DetectorsCode0
Self-Supervised GAN CompressionCode0
Are Compressed Language Models Less Subgroup Robust?Code0
Show:102550
← PrevPage 26 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