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 4626–4650 of 4925 papers

TitleStatusHype
Activations and Gradients Compression for Model-Parallel TrainingCode0
Overcoming Distribution Mismatch in Quantizing Image Super-Resolution NetworksCode0
Variational Inference with Latent Space Quantization for Adversarial ResilienceCode0
KP2Dtiny: Quantized Neural Keypoint Detection and Description on the EdgeCode0
TensorQuant - A Simulation Toolbox for Deep Neural Network QuantizationCode0
Real-Time Spacecraft Pose Estimation Using Mixed-Precision Quantized Neural Network on COTS Reconfigurable MPSoCCode0
U-Net Fixed-Point Quantization for Medical Image SegmentationCode0
Efficient Large-scale Approximate Nearest Neighbor Search on the GPUCode0
Addition is almost all you need: Compressing neural networks with double binary factorizationCode0
Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic LocomotionCode0
JPEG Inspired Deep LearningCode0
Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural NetworksCode0
Deep Learning as a Mixed Convex-Combinatorial Optimization ProblemCode0
Deep Image Compression via End-to-End LearningCode0
Joint Maximum Purity Forest with Application to Image Super-ResolutionCode0
Efficient Integer-Arithmetic-Only Convolutional Neural NetworksCode0
Efficient High-Resolution Template Matching with Vector Quantized Nearest Neighbour FieldsCode0
Deep Hashing via Householder QuantizationCode0
Iterative Training: Finding Binary Weight Deep Neural Networks with Layer BinarizationCode0
I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs QuantizationCode0
Is PGD-Adversarial Training Necessary? Alternative Training via a Soft-Quantization Network with Noisy-Natural Samples OnlyCode0
WAVEQ: GRADIENT-BASED DEEP QUANTIZATION OF NEURAL NETWORKS THROUGH SINUSOIDAL REGULARIZATIONCode0
Efficient Federated Intrusion Detection in 5G ecosystem using optimized BERT-based modelCode0
Parallel Blockwise Knowledge Distillation for Deep Neural Network CompressionCode0
Deep Convolutional AutoEncoder-based Lossy Image CompressionCode0
Show:102550
← PrevPage 186 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