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 2151–2200 of 4925 papers

TitleStatusHype
Magnificent Minified Models—0
ZeRO++: Extremely Efficient Collective Communication for Giant Model Training—0
HiNeRV: Video Compression with Hierarchical Encoding-based Neural RepresentationCode1
Evaluation and Optimization of Gradient Compression for Distributed Deep LearningCode1
Neural Network Compression using Binarization and Few Full-Precision Weights—0
PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-DiscriminatorsCode0
High-performance deep spiking neural networks with 0.3 spikes per neuron—0
GQFedWAvg: Optimization-Based Quantized Federated Learning in General Edge Computing SystemsCode0
INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank AdaptationCode4
SqueezeLLM: Dense-and-Sparse QuantizationCode6
Discrete Graph Auto-Encoder—0
MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition—0
NF4 Isn't Information Theoretically Optimal (and that's Good)Code1
Resource Efficient Neural Networks Using Hessian Based Pruning—0
Efficient and Robust Quantization-aware Training via Adaptive Coreset SelectionCode1
Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search—0
High-Fidelity Audio Compression with Improved RVQGANCode3
End-to-End Neural Network Compression via _1_2 Regularized Latency Surrogates—0
Mixed-TD: Efficient Neural Network Accelerator with Layer-Specific Tensor DecompositionCode0
Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inference—0
Iterative Signal Processing for Integrated Sensing and Communication Systems—0
Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization—0
MobileNMT: Enabling Translation in 15MB and 30msCode1
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight CompressionCode2
Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware—0
OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language ModelsCode1
Temporal Dynamic Quantization for Diffusion Models—0
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference—0
An Information-Theoretic Analysis of Self-supervised Discrete Representations of SpeechCode0
Binary and Ternary Natural Language GenerationCode1
Group channel pruning and spatial attention distilling for object detection—0
Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN TrainingCode1
Quantization-Aware and Tensor-Compressed Training of Transformers for Natural Language Understanding—0
Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition—0
FlexRound: Learnable Rounding based on Element-wise Division for Post-Training QuantizationCode0
On the Effectiveness of Hybrid Mutual Information Estimation—0
Dynamic quantized consensus under DoS attacks: Towards a tight zooming-out factor—0
AWQ: Activation-aware Weight Quantization for LLM Compression and AccelerationCode6
Asymptotic Performance Analysis of Large-Scale Active IRS-Aided Wireless Network—0
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNCode1
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised TrainingCode2
Compression with Bayesian Implicit Neural RepresentationsCode1
AdANNS: A Framework for Adaptive Semantic SearchCode1
PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models—0
Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function—0
Implementation of a framework for deploying AI inference engines in FPGAs—0
Intriguing Properties of Quantization at Scale—0
Towards Accurate Post-training Quantization for Diffusion ModelsCode1
Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution—0
Global-QSGD: Practical Floatless Quantization for Distributed Learning with Theoretical Guarantees—0
Show:102550
← PrevPage 44 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