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
Hierarchical Prior-based Super Resolution for Point Cloud Geometry CompressionCode1
Hierarchical Quantized AutoencodersCode1
Adaptive Gradient Quantization for Data-Parallel SGDCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
Generative Low-bitwidth Data Free QuantizationCode1
HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image RetrievalCode1
Graph Convolutional Network for Recommendation with Low-pass Collaborative FiltersCode1
Deep Learning-Enabled One-Bit DoA EstimationCode1
APQ: Joint Search for Network Architecture, Pruning and Quantization PolicyCode1
Hybrid Contrastive Quantization for Efficient Cross-View Video RetrievalCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
From Analog to Digital: Multi-Order Digital Joint Coding-Modulation for Semantic CommunicationCode1
Fully Quantized Image Super-Resolution NetworksCode1
Compress Any Segment Anything Model (SAM)Code1
Anonymizing Speech: Evaluating and Designing Speaker Anonymization TechniquesCode1
Deep Transferring QuantizationCode1
FrameQuant: Flexible Low-Bit Quantization for TransformersCode1
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
Adaptive Debanding FilterCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
FretNet: Continuous-Valued Pitch Contour Streaming for Polyphonic Guitar Tablature TranscriptionCode1
GAN Slimming: All-in-One GAN Compression by A Unified Optimization FrameworkCode1
DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsCode1
IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network QuantizationCode1
SimCC: a Simple Coordinate Classification Perspective for Human Pose EstimationCode1
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and QuantizationCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
ARB-LLM: Alternating Refined Binarizations for Large Language ModelsCode1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
FracBits: Mixed Precision Quantization via Fractional Bit-WidthsCode1
Differentiable JPEG: The Devil is in the DetailsCode1
Mixed Precision DNNs: All you need is a good parametrizationCode1
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval PerformanceCode1
Adaptive Data-Free QuantizationCode1
A Refined Analysis of Massive Activations in LLMsCode1
Pruning Small Pre-Trained Weights Irreversibly and Monotonically Impairs "Difficult" Downstream Tasks in LLMsCode1
kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors SearchCode1
Fractional Skipping: Towards Finer-Grained Dynamic CNN InferenceCode1
FP8 Quantization: The Power of the ExponentCode1
Disentanglement via Latent QuantizationCode1
CommVQ: Commutative Vector Quantization for KV Cache CompressionCode1
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
FQ-ViT: Post-Training Quantization for Fully Quantized Vision TransformerCode1
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN TrainingCode1
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsCode1
ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of MultipliersCode1
Graph-less Neural Networks: Teaching Old MLPs New Tricks via DistillationCode1
Structured Multi-Track Accompaniment Arrangement via Style Prior ModellingCode1
Communication-Efficient Adaptive Federated LearningCode1
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