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 401–450 of 4925 papers

TitleStatusHype
HHF: Hashing-guided Hinge Function for Deep Hashing RetrievalCode1
Hierarchical Prior-based Super Resolution for Point Cloud Geometry CompressionCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Generalizable Mixed-Precision Quantization via Attribution Rank PreservationCode1
Genetic Quantization-Aware Approximation for Non-Linear Operations in TransformersCode1
HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image RetrievalCode1
Graph Convolutional Network for Recommendation with Low-pass Collaborative FiltersCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
APQ: Joint Search for Network Architecture, Pruning and Quantization PolicyCode1
Deep PeNSieve: A deep learning framework based on the posit number systemCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
GAN Slimming: All-in-One GAN Compression by A Unified Optimization FrameworkCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
Image Compression with Recurrent Neural Network and Generalized Divisive NormalizationCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
Anonymizing Speech: Evaluating and Designing Speaker Anonymization TechniquesCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
Adaptive Debanding FilterCode1
Fully Quantized Image Super-Resolution NetworksCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN TrainingCode1
FrameQuant: Flexible Low-Bit Quantization for TransformersCode1
INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision TransformersCode1
DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsCode1
DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined RotationCode1
Compress Any Segment Anything Model (SAM)Code1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
ARB-LLM: Alternating Refined Binarizations for Large Language ModelsCode1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
Adaptive Data-Free QuantizationCode1
Fractional Skipping: Towards Finer-Grained Dynamic CNN InferenceCode1
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval PerformanceCode1
Joint Privacy Enhancement and Quantization in Federated LearningCode1
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and DistillationCode1
A Refined Analysis of Massive Activations in LLMsCode1
kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors SearchCode1
Disentanglement via Latent QuantizationCode1
FretNet: Continuous-Valued Pitch Contour Streaming for Polyphonic Guitar Tablature TranscriptionCode1
FP8 Quantization: The Power of the ExponentCode1
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and QuantizationCode1
FQ-ViT: Post-Training Quantization for Fully Quantized Vision TransformerCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
FracBits: Mixed Precision Quantization via Fractional Bit-WidthsCode1
From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic CommunicationCode1
BAFFLE: A Baseline of Backpropagation-Free Federated LearningCode1
Structured Multi-Track Accompaniment Arrangement via Style Prior ModellingCode1
Graph-less Neural Networks: Teaching Old MLPs New Tricks via DistillationCode1
Show:102550
← PrevPage 9 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