SOTAVerified

Quantization

Quantization is a promising technique to reduce the computation cost of neural network training, which can replace high-cost floating-point numbers (e.g., float32) with low-cost fixed-point numbers (e.g., int8/int16).

Source: Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 351–400 of 4925 papers

TitleStatusHype
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated LearningCode1
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-ResolutionCode1
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint ReductionCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
Accelerating Antimicrobial Peptide Discovery with Latent StructureCode1
Fast Nearest Convolution for Real-Time Efficient Image Super-ResolutionCode1
Few shot font generation via transferring similarity guided global style and quantization local styleCode1
FOX-NAS: Fast, On-device and Explainable Neural Architecture SearchCode1
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural NetworksCode1
KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range MultilaterationCode1
Fast and Low-Cost Genomic Foundation Models via Outlier RemovalCode1
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile DevicesCode1
Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded RepresentationsCode1
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language ModelsCode1
Examining Post-Training Quantization for Mixture-of-Experts: A BenchmarkCode1
Exploiting LLM QuantizationCode1
Exploring Quantization for Efficient Pre-Training of Transformer Language ModelsCode1
Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural NetworksCode1
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and ToolboxCode1
EQ-Net: Elastic Quantization Neural NetworksCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
Evaluation and Optimization of Gradient Compression for Distributed Deep LearningCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
Enhancing Generalization of Universal Adversarial Perturbation through Gradient AggregationCode1
End-to-End Rate-Distortion Optimized 3D Gaussian RepresentationCode1
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint ShrinkingCode1
Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN TrainingCode1
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network QuantizationCode1
Exploring the Connection Between Binary and Spiking Neural NetworksCode1
Adaptive Gradient Quantization for Data-Parallel SGDCode1
F8Net: Fixed-Point 8-bit Only Multiplication for Network QuantizationCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNCode1
FastText.zip: Compressing text classification modelsCode1
Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and PrivacyCode1
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision TransformersCode1
Feature Quantization Improves GAN TrainingCode1
Federated Optimization Algorithms with Random Reshuffling and Gradient CompressionCode1
ApiQ: Finetuning of 2-Bit Quantized Large Language ModelCode1
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor CoresCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Fast Distance-based Anomaly Detection in Images Using an Inception-like AutoencoderCode1
Efficient-VDVAE: Less is moreCode1
Embedding in Recommender Systems: A SurveyCode1
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
Efficient and Robust Quantization-aware Training via Adaptive Coreset SelectionCode1
Anonymizing Speech: Evaluating and Designing Speaker Anonymization TechniquesCode1
Show:102550
← PrevPage 8 of 99Next →
All datasetsImageNetCIFAR-10Wiki-40BAgeDB-30CFP-FPCOCO (Common Objects in Context)IJB-BIJB-CKnowledge-based:LFW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FQ-ViT (ViT-L)Top-1 Accuracy (%)85.03—Unverified
2FQ-ViT (ViT-B)Top-1 Accuracy (%)83.31—Unverified
3FQ-ViT (Swin-B)Top-1 Accuracy (%)82.97—Unverified
4FQ-ViT (Swin-S)Top-1 Accuracy (%)82.71—Unverified
5FQ-ViT (DeiT-B)Top-1 Accuracy (%)81.2—Unverified
6FQ-ViT (Swin-T)Top-1 Accuracy (%)80.51—Unverified
7FQ-ViT (DeiT-S)Top-1 Accuracy (%)79.17—Unverified
8Xception W8A8Top-1 Accuracy (%)78.97—Unverified
9ADLIK-MO-ResNet50-W4A4Top-1 Accuracy (%)77.88—Unverified
10ADLIK-MO-ResNet50-W3A4Top-1 Accuracy (%)77.34—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_3MAP160,327.04—Unverified
2DTQMAP0.79—Unverified
#ModelMetricClaimedVerifiedStatus
1OutEffHop-Bert_basePerplexity6.3—Unverified
2OutEffHop-Bert_basePerplexity6.21—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy98.13—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy92.92—Unverified
#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-495.13—Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-496.38—Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_5All84,809,664—Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy99.8—Unverified