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 551–600 of 4925 papers

TitleStatusHype
FastText.zip: Compressing text classification modelsCode1
Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded RepresentationsCode1
Fast Distance-based Anomaly Detection in Images Using an Inception-like AutoencoderCode1
F8Net: Fixed-Point 8-bit Only Multiplication for Network QuantizationCode1
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile DevicesCode1
Fast and Low-Cost Genomic Foundation Models via Outlier RemovalCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
Fine-tuning Quantized Neural Networks with Zeroth-order OptimizationCode1
Exploiting LLM QuantizationCode1
ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint ShrinkingCode1
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language ModelsCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
Evaluation and Optimization of Gradient Compression for Distributed Deep LearningCode1
Examining Post-Training Quantization for Mixture-of-Experts: A BenchmarkCode1
Exploring Quantization for Efficient Pre-Training of Transformer Language ModelsCode1
Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural NetworksCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
EQ-Net: Elastic Quantization Neural NetworksCode1
Bayesian Bits: Unifying Quantization and PruningCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Enhancing Generalization of Universal Adversarial Perturbation through Gradient AggregationCode1
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and ToolboxCode1
Exploring the Connection Between Binary and Spiking Neural NetworksCode1
Embedding in Recommender Systems: A SurveyCode1
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
Efficient and Robust Quantization-aware Training via Adaptive Coreset SelectionCode1
BAND-2k: Banding Artifact Noticeable Database for Banding Detection and Quality AssessmentCode1
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsCode1
EMQ: Evolving Training-free Proxies for Automated Mixed Precision QuantizationCode1
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the EdgeCode1
EFaR 2023: Efficient Face Recognition CompetitionCode1
BAGUA: Scaling up Distributed Learning with System RelaxationsCode1
Accurate KV Cache Quantization with Outlier Tokens TracingCode1
Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital FossaCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
A Memory Efficient Baseline for Open Domain Question AnsweringCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
DVD-Quant: Data-free Video Diffusion Transformers QuantizationCode1
Efficient-VDVAE: Less is moreCode1
Dynamic Network Quantization for Efficient Video InferenceCode1
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
End-to-End Rate-Distortion Optimized 3D Gaussian RepresentationCode1
ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank CompensationCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionCode1
EasyQuant: Post-training Quantization via Scale OptimizationCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
BBS: Bi-directional Bit-level Sparsity for Deep Learning AccelerationCode1
Beyond Learned Metadata-based Raw Image ReconstructionCode1
Enabling Binary Neural Network Training on the EdgeCode1
Show:102550
← PrevPage 12 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