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 3201–3225 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
Show:102550
← PrevPage 129 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