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 1–10 of 4925 papers

TitleStatusHype
Efficient Deployment of Spiking Neural Networks on SpiNNaker2 for DVS Gesture Recognition Using Neuromorphic Intermediate RepresentationCode0
An End-to-End DNN Inference Framework for the SpiNNaker2 Neuromorphic MPSoC—0
Angle Estimation of a Single Source with Massive Uniform Circular Arrays—0
Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine—0
Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications—0
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
Lightweight Federated Learning over Wireless Edge Networks—0
Compress Any Segment Anything Model (SAM)Code1
Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation—0
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group QuantizationCode2
Show:102550
← PrevPage 1 of 493Next →
All datasetsImageNetCIFAR-10Wiki-40BAgeDB-30CFP-FPCOCO (Common Objects in Context)IJB-BIJB-CKnowledge-based:LFW

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3—Unverified