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 726–750 of 4925 papers

TitleStatusHype
Image Compression with Recurrent Neural Network and Generalized Divisive NormalizationCode1
Optimal Target Shape for LiDAR Pose EstimationCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
Dynamic Network Quantization for Efficient Video InferenceCode1
FOX-NAS: Fast, On-device and Explainable Neural Architecture SearchCode1
Generalizable Mixed-Precision Quantization via Attribution Rank PreservationCode1
Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval PerformanceCode1
Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd CountingCode1
SimCC: a Simple Coordinate Classification Perspective for Human Pose EstimationCode1
BAGUA: Scaling up Distributed Learning with System RelaxationsCode1
Secure Quantized Training for Deep LearningCode1
APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor CoresCode1
VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice ConversionCode1
Task-driven Semantic Coding via Reinforcement LearningCode1
Transferable Sparse Adversarial AttackCode1
Linear-Time Self Attention with Codeword Histogram for Efficient RecommendationCode1
Post-Training Sparsity-Aware QuantizationCode1
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile DevicesCode1
Anchor-based Plain Net for Mobile Image Super-ResolutionCode1
Continual Learning via Bit-Level Information PreservingCode1
Joint Learning of Deep Retrieval Model and Product Quantization based Embedding IndexCode1
Pareto-Optimal Quantized ResNet Is Mostly 4-bitCode1
Binarized Aggregated Network with Quantization: Flexible Deep Learning Deployment for CSI Feedback in Massive MIMO SystemCode1
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed TrainingCode1
Show:102550
← PrevPage 30 of 197Next →
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