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 3376–3400 of 4925 papers

TitleStatusHype
Denoising Noisy Neural Networks: A Bayesian Approach with CompensationCode0
EuclidNets: Combining hardware and architecture design for Efficient Inference and Training—0
Revisiting Multi-Codebook QuantizationCode0
DoStoVoQ: Doubly Stochastic Voronoi Vector Quantization SGD for Federated Learning—0
Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile DevicesCode1
Model Compression—0
Distribution Agnostic Symbolic Representations for Time Series Dimensionality Reduction and Online Anomaly DetectionCode0
Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM FrameworkCode0
Anchor-based Plain Net for Mobile Image Super-ResolutionCode1
BatchQuant: Quantized-for-all Architecture Search with Robust QuantizerCode0
Self-supervised Remote Sensing Images Change Detection at Pixel-level—0
Is In-Domain Data Really Needed? A Pilot Study on Cross-Domain Calibration for Network Quantization—0
FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal RetrievalCode0
Lightweight Compression of Intermediate Neural Network Features for Collaborative Intelligence—0
Quantized Proximal Averaging Network for Analysis Sparse Coding—0
Discrete representations in neural models of spoken languageCode0
A CNN-based Prediction-Aware Quality Enhancement Framework for VVC—0
Deep and Shallow Covariance Feature Quantization for 3D Facial Expression Recognition—0
3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration—0
Estimation and Quantization of Expected Persistence Diagrams—0
Continual Learning via Bit-Level Information PreservingCode1
In-Hindsight Quantization Range Estimation for Quantized Training—0
Joint Learning of Deep Retrieval Model and Product Quantization based Embedding IndexCode1
RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things—0
Pareto-Optimal Quantized ResNet Is Mostly 4-bitCode1
Show:102550
← PrevPage 136 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