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 3676–3700 of 4925 papers

TitleStatusHype
Quantization optimized with respect to the Haar basis—0
Who's a Good Boy? Reinforcing Canine Behavior in Real-Time using Machine LearningCode0
Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks—0
End-to-end Quantized Training via Log-Barrier Extensions—0
Product Quantizer Aware Inverted Index for Scalable Nearest Neighbor Search—0
Practical Locally Private Federated Learning with Communication Efficiency—0
Uniform-Precision Neural Network Quantization via Neural Channel Expansion—0
Incremental few-shot learning via vector quantization in deep embedded space—0
Improving Low-Precision Network Quantization via Bin Regularization—0
TwinDNN: A Tale of Two Deep Neural Networks—0
Explore the Potential of CNN Low Bit Training—0
DQSGD: DYNAMIC QUANTIZED STOCHASTIC GRADIENT DESCENT FOR COMMUNICATION-EFFICIENT DISTRIBUTED LEARNING—0
Simple Augmentation Goes a Long Way: ADRL for DNN Quantization—0
Improving the accuracy of neural networks in analog computing-in-memory systems by a generalized quantization method—0
Post-Training Weighted Quantization of Neural Networks for Language Models—0
Collaborative Filtering with Smooth Reconstruction of the Preference Function—0
Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bitwise Regularization—0
WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic—0
WAVEQ: GRADIENT-BASED DEEP QUANTIZATION OF NEURAL NETWORKS THROUGH SINUSOIDAL REGULARIZATIONCode0
Hybrid and Non-Uniform DNN quantization methods using Retro Synthesis data for efficient inference—0
Multi-Prize Lottery Ticket Hypothesis: Finding Generalizable and Efficient Binary Subnetworks in a Randomly Weighted Neural Network—0
Weights Having Stable Signs Are Important: Finding Primary Subnetworks and Kernels to Compress Binary Weight Networks—0
Learned Multi-Resolution Variable-Rate Image Compression with Octave-based Residual Blocks—0
BinaryBERT: Pushing the Limit of BERT Quantization—0
Improving Adversarial Robustness in Weight-quantized Neural Networks—0
Show:102550
← PrevPage 148 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