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 2301–2350 of 4925 papers

TitleStatusHype
MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy CodingCode1
Blockwise Compression of Transformer-based Models without Retraining—0
RPTQ: Reorder-based Post-training Quantization for Large Language ModelsCode1
Real-time 6K Image Rescaling with Rate-distortion OptimizationCode1
Distributed Optimization for Quadratic Cost Functions over Large-Scale Networks with Quantized Communication and Finite-Time Convergence—0
A Unified Compression Framework for Efficient Speech-Driven Talking-Face Generation—0
Q-DETR: An Efficient Low-Bit Quantized Detection TransformerCode1
FP8 versus INT8 for efficient deep learning inference—0
oBERTa: Improving Sparse Transfer Learning via improved initialization, distillation, and pruning regimes—0
A Joint Model and Data Driven Method for Distributed Estimation—0
SC-VAE: Sparse Coding-based Variational Autoencoder with Learned ISTACode0
Low-Dose CT Image Reconstruction using Vector Quantized Convolutional Autoencoder with Perceptual Loss—0
Tetra-AML: Automatic Machine Learning via Tensor Networks—0
Object Discovery from Motion-Guided TokensCode1
Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis—0
An Evaluation of Memory Optimization Methods for Training Neural Networks—0
LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression—0
Towards Accurate Post-Training Quantization for Vision Transformer—0
Hard Sample Matters a Lot in Zero-Shot QuantizationCode1
The Quantization Model of Neural ScalingCode0
Scaled Quantization for the Vision Transformer—0
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance—0
Low Rank Optimization for Efficient Deep Learning: Making A Balance between Compact Architecture and Fast Training—0
Posthoc Interpretation via Quantization—0
Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers with Bridge Block Reconstruction for IoT SystemsCode0
Fighting over-fitting with quantization for learning deep neural networks on noisy labels—0
Quantized Zero Dynamics Attacks against Sampled-data Control Systems—0
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical PerspectiveCode1
SpaceEvo: Hardware-Friendly Search Space Design for Efficient INT8 InferenceCode1
ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank CompensationCode1
Gradient-descent hardware-aware training and deployment for mixed-signal Neuromorphic processorsCode1
R2 Loss: Range Restriction Loss for Model Compression and Quantization—0
Rediscovering Hashed Random Projections for Efficient Quantization of Contextualized Sentence EmbeddingsCode0
Adaptive Data-Free QuantizationCode1
Bag of Tricks with Quantized Convolutional Neural Networks for image classification—0
Modular Quantization-Aware Training for 6D Object Pose EstimationCode0
Regularized Vector Quantization for Tokenized Image Synthesis—0
Entropy Coding Improvement for Low-complexity Compressive Auto-encoders—0
QVRF: A Quantization-error-aware Variable Rate Framework for Learned Image CompressionCode1
Greener yet Powerful: Taming Large Code Generation Models with Quantization—0
Dynamic Stashing Quantization for Efficient Transformer Training—0
Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural NetworksCode1
Vector Quantized Time Series Generation with a Bidirectional Prior ModelCode1
QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms—0
Neural Vector Fields: Implicit Representation by Explicit LearningCode1
A Privacy Preserving System for Movie Recommendations Using Federated Learning—0
ML Codebook Design for Initial Access and CSI Type-II Feedback in Sub-6GHz 5G NR—0
Fixed-point quantization aware training for on-device keyword-spotting—0
MetaGrad: Adaptive Gradient Quantization with Hypernetworks—0
Rotation Invariant Quantization for Model CompressionCode0
Show:102550
← PrevPage 47 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