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 4801–4850 of 4925 papers

TitleStatusHype
High-Dimensional Distribution Generation Through Deep Neural Networks—0
High Dimensional Statistical Estimation under Uniformly Dithered One-bit Quantization—0
High-Dimensional Stochastic Gradient Quantization for Communication-Efficient Edge Learning—0
High-Fidelity Facial Albedo Estimation via Texture Quantization—0
High Five: Improving Gesture Recognition by Embracing Uncertainty—0
Highly Efficient and Effective LLMs with Multi-Boolean Architectures—0
Highly Efficient SNNs for High-speed Object Detection—0
High-Order Signed Distance Transform of Sampled Signals—0
High-Perceptual Quality JPEG Decoding via Posterior Sampling—0
High Performance Natural Language Processing—0
High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise—0
High-quality Single-model Deep Video Compression with Frame-Conv3D and Multi-frame Differential Modulation—0
High-Resolution Volumetric Reconstruction for Clothed Humans—0
High-Resolution WiFi Imaging with Reconfigurable Intelligent Surfaces—0
High-Throughput Blind Co-Channel Interference Cancellation for Edge Devices Using Depthwise Separable Convolutions, Quantization, and Pruning—0
HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation—0
HiKonv: Maximizing the Throughput of Quantized Convolution With Novel Bit-wise Management and Computation—0
Histogram-Equalized Quantization for logic-gated Residual Neural Networks—0
HitNet: Hybrid Ternary Recurrent Neural Network—0
HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization—0
HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory—0
HoloFormer: Deep Compression of Pre-Trained Transforms via Unified Optimization of N:M Sparsity and Integer Quantization—0
On the Impact of Calibration Data in Post-training Quantization and Pruning—0
How Does Quantization Affect Multilingual LLMs?—0
How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text—0
How Should We Extract Discrete Audio Tokens from Self-Supervised Models?—0
How to Attain Communication-Efficient DNN Training? Convert, Compress, Correct—0
How to design a derivatives market?—0
How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training—0
HPGN: Hybrid Priors-Guided Network for Compressed Low-Light Image Enhancement—0
HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization—0
HQNAS: Auto CNN deployment framework for joint quantization and architecture search—0
HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes—0
HRPVT: High-Resolution Pyramid Vision Transformer for medium and small-scale human pose estimation—0
Huber-energy measure quantization—0
Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference—0
Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks—0
Human-level molecular optimization driven by mol-gene evolution—0
Human Symmetry Uncertainty Detected by a Self-Organizing Neural Network Map—0
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models—0
HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays—0
HW-TSC’s Participation in the WMT 2021 Efficiency Shared Task—0
Hybrid and Non-Uniform DNN quantization methods using Retro Synthesis data for efficient inference—0
Hybrid and Non-Uniform quantization methods using retro synthesis data for efficient inference—0
Hybrid Beamforming for Integrated Sensing and Communications With Low Resolution DACs—0
HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression—0
Hybrid model for Single-Stage Multi-Person Pose Estimation—0
Hybrid noise shaping for audio coding using perfectly overlapped window—0
Hybrid of DiffStride and Spectral Pooling in Convolutional Neural Networks—0
Hybrid Receiver Design for Massive MIMO-OFDM with Low-Resolution ADCs and Oversampling—0
Show:102550
← PrevPage 97 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