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 276–300 of 4925 papers

TitleStatusHype
Context-aware Communication for Multi-agent Reinforcement LearningCode1
Finite Scalar Quantization: VQ-VAE Made SimpleCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Continuous Visual Autoregressive Generation via Score MaximizationCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix ApproximationCode1
Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement LearningCode1
Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded PlatformsCode1
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated LearningCode1
Few-Bit Backward: Quantized Gradients of Activation Functions for Memory Footprint ReductionCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
Federated Optimization Algorithms with Random Reshuffling and Gradient CompressionCode1
Few shot font generation via transferring similarity guided global style and quantization local styleCode1
AFPQ: Asymmetric Floating Point Quantization for LLMsCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
Feature Quantization Improves GAN TrainingCode1
FFNeRV: Flow-Guided Frame-Wise Neural Representations for VideosCode1
Compress Any Segment Anything Model (SAM)Code1
AffineQuant: Affine Transformation Quantization for Large Language ModelsCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNCode1
Show:102550
← PrevPage 12 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