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 3201–3250 of 4925 papers

TitleStatusHype
Differentiable Discrete Device-to-System Codesign for Optical Neural Networks via Gumbel-Softmax—0
Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization—0
Lidar Range Image Compression with Deep Delta Encoding—0
Contrastive Quant: Quantization Makes Stronger Contrastive Learning—0
Efficient Point Transformer for Large-scale 3D Scene Understanding—0
HoloFormer: Deep Compression of Pre-Trained Transforms via Unified Optimization of N:M Sparsity and Integer Quantization—0
Revisiting Locality-Sensitive Binary Codes from Random Fourier Features—0
Transformer-based Transform CodingCode1
CSQ: Centered Symmetric Quantization for Extremely Low Bit Neural Networks—0
One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning ObjectiveCode1
Click-through Rate Prediction with Auto-Quantized Contrastive Learning—0
Understanding and Overcoming the Challenges of Efficient Transformer QuantizationCode1
Performance Analysis of IRS-Assisted Cell-Free Communication—0
Vision Transformer Hashing for Image RetrievalCode1
Unbiased Single-scale and Multi-scale Quantizers for Distributed OptimizationCode1
Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation AnalysisCode0
Distribution-sensitive Information Retention for Accurate Binary Neural Network—0
Predicting Attention Sparsity in Transformers—0
QTTNet: Quantized Tensor Train Neural Networks for 3D Object and Video Recognition.Code0
Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework—0
Robustness Analysis of Deep Learning Frameworks on Mobile PlatformsCode0
iRNN: Integer-only Recurrent Neural Network—0
Channel Estimation in MIMO Systems with One-bit Spatial Sigma-delta ADCs—0
HPTQ: Hardware-Friendly Post Training QuantizationCode1
OMPQ: Orthogonal Mixed Precision QuantizationCode1
Phrase Retrieval Learns Passage Retrieval, TooCode1
Experimental implementation of a neural network optical channel equalizer in restricted hardware using pruning and quantization—0
Revisiting Quantization Error in Face Alignment—0
2-in-1 Accelerator: Enabling Random Precision Switch for Winning Both Adversarial Robustness and Efficiency—0
PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval—0
1st-Order Dynamics on Nonlinear Agents for Resource Allocation over Uniformly-Connected Networks—0
Fine-grained Data Distribution Alignment for Post-Training QuantizationCode1
ECQ^x: Explainability-Driven Quantization for Low-Bit and Sparse DNNsCode0
Bag of Tricks for Optimizing Transformer EfficiencyCode0
Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks—0
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT CompressionCode1
Self-supervised Product Quantization for Deep Unsupervised Image RetrievalCode0
Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss—0
Image Compression with Recurrent Neural Network and Generalized Divisive NormalizationCode1
Characterization of the frequency response of channel-interleaved photonic ADCs based on the optical time-division demultiplexer—0
Risk Assessment for Connected Vehicles under Stealthy Attacks on Vehicle-to-Vehicle Networks—0
Optimal Target Shape for LiDAR Pose EstimationCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations—0
Quantization of Generative Adversarial Networks for Efficient Inference: a Methodological Study—0
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
4-bit Quantization of LSTM-based Speech Recognition Models—0
A Quantitative Approach To The Temporal Dependency in Video Coding—0
On Adaptive Transmission for Distributed Detection in Energy Harvesting Wireless Sensor Networks with Limited Fusion Center Feedback—0
Dynamic Network Quantization for Efficient Video InferenceCode1
Show:102550
← PrevPage 65 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