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 1226–1250 of 4925 papers

TitleStatusHype
Beyond Product Quantization: Deep Progressive Quantization for Image RetrievalCode0
Instance-Aware Dynamic Neural Network QuantizationCode0
Improving Robustness Against Stealthy Weight Bit-Flip Attacks by Output Code MatchingCode0
Improving Neural Network Quantization without Retraining using Outlier Channel SplittingCode0
Improving Self-Supervised Learning-based MOS Prediction NetworksCode0
Improved Gradient based Adversarial Attacks for Quantized NetworksCode0
Digital and Hybrid Precoding Designs in Massive MIMO with Low-Resolution ADCsCode0
Implicit Feature Decoupling with Depthwise QuantizationCode0
In-Context Learning for MIMO Equalization Using Transformer-Based Sequence ModelsCode0
Diffusion Models as Stochastic Quantization in Lattice Field TheoryCode0
Image Hashing by Minimizing Discrete Component-wise Wasserstein DistanceCode0
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMsCode0
IBVC: Interpolation-driven B-frame Video CompressionCode0
A Bag-of-Words Equivalent Recurrent Neural Network for Action RecognitionCode0
Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance AnalysisCode0
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision WeightsCode0
Improved Knowledge Distillation for Crowd Counting on IoT DeviceCode0
Beyond Perplexity: Multi-dimensional Safety Evaluation of LLM CompressionCode0
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural NetworksCode0
Hybrid coarse-fine classification for head pose estimationCode0
Differentiable Product Quantization for End-to-End Embedding CompressionCode0
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and MemoryCode0
Differentiable Product Quantization for Memory Efficient Camera RelocalizationCode0
HOT: Hadamard-based Optimized TrainingCode0
HyperFlow: Representing 3D Objects as SurfacesCode0
Show:102550
← PrevPage 50 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