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 3951–4000 of 4925 papers

TitleStatusHype
Probability Weighted Compact Feature for Domain Adaptive RetrievalCode1
Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications—0
Optimizing JPEG Quantization for Classification Networks—0
A Survey on Deep Hashing Methods—0
VQ-DRAW: A Sequential Discrete VAECode1
Phoenix: A Low-Precision Floating-Point Quantization Oriented Architecture for Convolutional Neural Networks—0
WaveQ: Gradient-Based Deep Quantization of Neural Networks through Sinusoidal Adaptive Regularization—0
Image Hashing by Minimizing Discrete Component-wise Wasserstein DistanceCode0
Automatic Perturbation Analysis for Scalable Certified Robustness and BeyondCode1
Quantized Neural Network Inference with Precision Batching—0
Moniqua: Modulo Quantized Communication in Decentralized SGD—0
Generalized Product Quantization Network for Semi-supervised Image RetrievalCode1
Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of TransformersCode1
Adversarial Attack on Deep Product Quantization Network for Image Retrieval—0
Optimal Gradient Quantization Condition for Communication-Efficient Distributed Training—0
Non-Volatile Memory Array Based Quantization- and Noise-Resilient LSTM Neural Networks—0
Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees—0
Searching for Winograd-aware Quantized NetworksCode1
OptComNet: Optimized Neural Networks for Low-Complexity Channel Estimation—0
Exploring the Connection Between Binary and Spiking Neural NetworksCode1
Revisiting Saliency Metrics: Farthest-Neighbor Area Under CurveCode0
Quantized Decentralized Stochastic Learning over Directed Graphs—0
PoET-BiN: Power Efficient Tiny Binary Neurons—0
New Bounds For Distributed Mean Estimation and Variance Reduction—0
Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems—0
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision—0
Neural Network Compression Framework for fast model inferenceCode2
Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor—0
Hierarchical Quantized AutoencodersCode1
SYMOG: learning symmetric mixture of Gaussian modes for improved fixed-point quantization—0
Algorithm-hardware Co-design for Deformable ConvolutionCode1
Variational Bayesian QuantizationCode1
Gradient _1 Regularization for Quantization Robustness—0
Robust Quantization: One Model to Rule Them AllCode1
Learning Architectures for Binary NetworksCode1
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision ActivationsCode1
Realizing a Low-Power Head-Mounted Phase-Only Holographic Display by Light-Weight Compression—0
BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization—0
Accelerating Deep Learning Inference via Freezing—0
Switchable Precision Neural Networks—0
Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior—0
Random VLAD based Deep Hashing for Efficient Image Retrieval—0
Differentially Quantized Gradient Methods—0
Emotion Recognition Using Speaker Cues—0
Widening and Squeezing: Towards Accurate and Efficient QNNs—0
Automatic Pruning for Quantized Neural Networks—0
SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks—0
Towards Sharper First-Order Adversary with Quantized GradientsCode1
Optimal Controller Synthesis and Dynamic Quantizer Switching for Linear-Quadratic-Gaussian Systems—0
Improving LPCNet-based Text-to-Speech with Linear Prediction-structured Mixture Density Network—0
Show:102550
← PrevPage 80 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