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 4251–4275 of 4925 papers

TitleStatusHype
Distributed Constraint-Coupled Optimization over Lossy Networks—0
Distributed Convolutional Neural Network Training on Mobile and Edge Clusters—0
Distributed CPU Scheduling Subject to Nonlinear Constraints—0
Distributed Deep Convolutional Compression for Massive MIMO CSI Feedback—0
Distributed Deep Reinforcement Learning Based Gradient Quantization for Federated Learning Enabled Vehicle Edge Computing—0
Distributed Delay-Tolerant Strategies for Equality-Constraint Sum-Preserving Resource Allocation—0
Distributed Energy Resource Management: All-Time Resource-Demand Feasibility, Delay-Tolerance, Nonlinearity, and Beyond—0
Distributed Learning with Compressed Gradient Differences—0
Distributed Learning with Sublinear Communication—0
Distributed Mean Estimation with Limited Communication—0
New Bounds For Distributed Mean Estimation and Variance Reduction—0
Distributed Optimization for Quadratic Cost Functions over Large-Scale Networks with Quantized Communication and Finite-Time Convergence—0
Distributed Optimization via Gradient Descent with Event-Triggered Zooming over Quantized Communication—0
Distributed Optimization with Efficient Communication, Event-Triggered Solution Enhancement, and Operation Stopping—0
Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement—0
Distribution Adaptive INT8 Quantization for Training CNNs—0
Distribution-Aware Adaptive Multi-Bit Quantization—0
Distribution-Preserving k-Anonymity—0
Distribution-sensitive Information Retention for Accurate Binary Neural Network—0
Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training—0
Ditto: Accelerating Diffusion Model via Temporal Value Similarity—0
Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization—0
DiverGet: A Search-Based Software Testing Approach for Deep Neural Network Quantization Assessment—0
Diversifying Sample Generation for Accurate Data-Free Quantization—0
Divide and Conquer: Leveraging Intermediate Feature Representations for Quantized Training of Neural Networks—0
Show:102550
← PrevPage 171 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