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 651–700 of 4925 papers

TitleStatusHype
RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training QuantizationCode1
Soft Threshold Ternary NetworksCode1
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsCode1
It's All In the Teacher: Zero-Shot Quantization Brought Closer to the TeacherCode1
Pseudo-Label Transfer from Frame-Level to Note-Level in a Teacher-Student Framework for Singing Transcription from Polyphonic MusicCode1
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning SimulationsCode1
Efficient-VDVAE: Less is moreCode1
Overcoming Oscillations in Quantization-Aware TrainingCode1
Unified Multivariate Gaussian Mixture for Efficient Neural Image CompressionCode1
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Mixed-Precision Neural Network Quantization via Learned Layer-wise ImportanceCode1
Semi-Discrete Normalizing Flows through Differentiable TessellationCode1
CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and QuantizationCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision DiscretizationCode1
Patch Similarity Aware Data-Free Quantization for Vision TransformersCode1
Arrhythmia Classifier Using Convolutional Neural Network with Adaptive Loss-aware Multi-bit Networks QuantizationCode1
Retriever: Learning Content-Style Representation as a Token-Level Bipartite GraphCode1
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian ApproximationCode1
BED: A Real-Time Object Detection System for Edge DevicesCode1
Benchmarking of DL Libraries and Models on Mobile DevicesCode1
Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast DeploymentCode1
F8Net: Fixed-Point 8-bit Only Multiplication for Network QuantizationCode1
Hybrid Contrastive Quantization for Efficient Cross-View Video RetrievalCode1
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint ReductionCode1
The fine line between dead neurons and sparsity in binarized spiking neural networksCode1
Post-training Quantization for Neural Networks with Provable GuaranteesCode1
Q-ViT: Fully Differentiable Quantization for Vision TransformerCode1
Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based RetrievalCode1
PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++Code1
Learnable Lookup Table for Neural Network QuantizationCode1
AlignQ: Alignment Quantization With ADMM-Based Correlation PreservationCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Learning Cross-Scale Weighted Prediction for Efficient Neural Video CompressionCode1
Training Quantized Deep Neural Networks via Cooperative CoevolutionCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Deep Hash Distillation for Image RetrievalCode1
N3H-Core: Neuron-designed Neural Network Accelerator via FPGA-based Heterogeneous Computing CoresCode1
HHF: Hashing-guided Hinge Function for Deep Hashing RetrievalCode1
Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through EstimationCode1
FQ-ViT: Post-Training Quantization for Fully Quantized Vision TransformerCode1
Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent RepresentationsCode1
Sharpness-aware Quantization for Deep Neural NetworksCode1
PTQ4ViT: Post-training quantization for vision transformers with twin uniform quantizationCode1
Mesa: A Memory-saving Training Framework for TransformersCode1
IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network QuantizationCode1
LiMuSE: Lightweight Multi-modal Speaker ExtractionCode1
MQBench: Towards Reproducible and Deployable Model Quantization BenchmarkCode1
Qimera: Data-free Quantization with Synthetic Boundary Supporting SamplesCode1
Show:102550
← PrevPage 14 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