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 3601–3650 of 4925 papers

TitleStatusHype
Neural Network-based OFDM Receiver for Resource Constrained IoT Devices—0
Neural Network-based Quantization for Network Automation—0
Neural Network Compression using Binarization and Few Full-Precision Weights—0
Neural Network Emulation of the Classical Limit in Quantum Systems via Learned Observable Mappings—0
Neural Network-Inspired Analog-to-Digital Conversion to Achieve Super-Resolution with Low-Precision RRAM Devices—0
Neural Network Quantization for Efficient Inference: A Survey—0
Neural Network Quantization with AI Model Efficiency Toolkit (AIMET)—0
Neural Networks: According to the Principles of Grassmann Algebra—0
Neural Networks Compression for Language Modeling—0
Neural Networks Weights Quantization: Target None-retraining Ternary (TNT)—0
Neural Network Training on In-memory-computing Hardware with Radix-4 Gradients—0
Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals—0
Neural Video Compression with Feature Modulation—0
Neuroevolution-Enhanced Multi-Objective Optimization for Mixed-Precision Quantization—0
Neuromimetic Linear Systems -- Resilience and Learning—0
New Loss Functions for Fast Maximum Inner Product Search—0
New pyramidal hybrid textural and deep features based automatic skin cancer classification model: Ensemble DarkNet and textural feature extractor—0
NGEMM: Optimizing GEMM for Deep Learning via Compiler-based Techniques—0
n-hot: Efficient bit-level sparsity for powers-of-two neural network quantization—0
Noiseless Privacy—0
Noise Sensitivity-Based Energy Efficient and Robust Adversary Detection in Neural Networks—0
NoiseVC: Towards High Quality Zero-Shot Voice Conversion—0
Noisy One-bit Compressed Sensing with Side-Information—0
Nonlinear Perturbation-based Non-Convex Optimization over Time-Varying Networks—0
Non-linear predictive vector quantization of speech—0
Nonlinear Sparse Bayesian Learning Methods with Application to Massive MIMO Channel Estimation with Hardware Impairments—0
Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees—0
Nonparametric Decentralized Detection and Sparse Sensor Selection via Multi-Sensor Online Kernel Scalar Quantization—0
Non-Structured DNN Weight Pruning -- Is It Beneficial in Any Platform?—0
Non-vacuous Generalization Bounds for Deep Neural Networks without any modification to the trained models—0
Non-Volatile Memory Array Based Quantization- and Noise-Resilient LSTM Neural Networks—0
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models—0
No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization—0
Novel Near-Optimal Scalar Quantizers with Exponential Decay Rate and Global Convergence—0
NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics—0
NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache—0
NTP : A Neural Network Topology Profiler—0
NUPES : Non-Uniform Post-Training Quantization via Power Exponent Search—0
NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization—0
NVRC: Neural Video Representation Compression—0
O(1) Communication for Distributed SGD through Two-Level Gradient Averaging—0
OAC: Output-adaptive Calibration for Accurate Post-training Quantization—0
Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization—0
oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes—0
Object Detection-Based Variable Quantization Processing—0
Object Proposal Generation using Two-Stage Cascade SVMs—0
ODG-Q: Robust Quantization via Online Domain Generalization—0
Tighter Regret Analysis and Optimization of Online Federated Learning—0
On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks—0
Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models—0
Show:102550
← PrevPage 73 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