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 701–725 of 4925 papers

TitleStatusHype
Embedding in Recommender Systems: A SurveyCode1
Patch Similarity Aware Data-Free Quantization for Vision TransformersCode1
Lightweight Super-Resolution Head for Human Pose EstimationCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Compress Any Segment Anything Model (SAM)Code1
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNCode1
Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike FluctuationsCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial LearningCode1
AlignQ: Alignment Quantization With ADMM-Based Correlation PreservationCode1
Lexico: Extreme KV Cache Compression via Sparse Coding over Universal DictionariesCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
Least squares binary quantization of neural networksCode1
Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural NetworksCode1
Position-based Scaled Gradient for Model Quantization and PruningCode1
BRECQ: Pushing the Limit of Post-Training Quantization by Block ReconstructionCode1
Post-training Quantization for Neural Networks with Provable GuaranteesCode1
L-GreCo: Layerwise-Adaptive Gradient Compression for Efficient and Accurate Deep LearningCode1
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and ToolboxCode1
Learning to Groove with Inverse Sequence TransformationsCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Anonymizing Speech: Evaluating and Designing Speaker Anonymization TechniquesCode1
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in ControlCode1
Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and CompressionCode1
Show:102550
← PrevPage 29 of 197Next →
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