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 2876–2900 of 4925 papers

TitleStatusHype
Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations—0
Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction—0
SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization—0
SPIQ: Data-Free Per-Channel Static Input Quantization—0
SplitQuant: Layer Splitting for Low-Bit Neural Network Quantization—0
SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity—0
sqSGD: Locally Private and Communication Efficient Federated Learning—0
SQuantizer: Simultaneous Learning for Both Sparse and Low-precision Neural Networks—0
SQuAT: Sharpness- and Quantization-Aware Training for BERT—0
SQuat: Subspace-orthogonal KV Cache Quantization—0
SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks—0
Stability Analysis of Various Symbolic Rule Extraction Methods from Recurrent Neural Network—0
Stabilization of an unstable reaction-diffusion PDE with input delay despite state and input quantization—0
Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix—0
StableQuant: Layer Adaptive Post-Training Quantization for Speech Foundation Models—0
Stacked Denoising Autoencoders and Transfer Learning for Immunogold Particles Detection and Recognition—0
StainPIDR: A Pathological Image Decouplingand Reconstruction Method for Stain Normalization Based on Color Vector Quantization and Structure Restaining—0
Standard Deviation-Based Quantization for Deep Neural Networks—0
STanH : Parametric Quantization for Variable Rate Learned Image Compression—0
State Machine-based Waveforms for Channels With 1-Bit Quantization and Oversampling With Time-Instance Zero-Crossing Modulation—0
Static Quantized Radix-2 FFT/IFFT Processor for Constraints Analysis—0
Statistical Model Compression for Small-Footprint Natural Language Understanding—0
Statistical Modeling of Soft Error Influence on Neural Networks—0
STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition—0
STEPS: Sequential Probability Tensor Estimation for Text-to-Image Hard Prompt Search—0
Show:102550
← PrevPage 116 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