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 3426–3450 of 4925 papers

TitleStatusHype
Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization—0
Acceleration for Compressed Gradient Descent in Distributed Optimization—0
Acceleration of Convolutional Neural Network Using FFT-Based Split Convolutions—0
Accelerator-Aware Training for Transducer-Based Speech Recognition—0
AccLLM: Accelerating Long-Context LLM Inference Via Algorithm-Hardware Co-Design—0
Accumulator-Aware Post-Training Quantization—0
Accuracy is Not All You Need—0
Accuracy to Throughput Trade-offs for Reduced Precision Neural Networks on Reconfigurable Logic—0
Accurate Block Quantization in LLMs with Outliers—0
Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization—0
Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search—0
Accurate INT8 Training Through Dynamic Block-Level Fallback—0
Accurate Sine-Wave Amplitude Measurements Using Nonlinearly Quantized Data—0
A Channelized Binning Method for Extraction of Dominant Color Pixel Value—0
Achieving binary weight and activation for LLMs using Post-Training Quantization—0
Achieving Robustness in Blind Modulo Analog-to-Digital Conversion—0
Differentially Quantized Gradient Methods—0
Lean classical-quantum hybrid neural network model for image classification—0
A Closed-loop Sleep Modulation System with FPGA-Accelerated Deep Learning—0
A CNN-based Prediction-Aware Quality Enhancement Framework for VVC—0
A Genetic Algorithm Approach for ImageRepresentation Learning through Color Quantization—0
A Compact and Discriminative Face Track Descriptor—0
A comparative study of several parameterizations for speaker recognition—0
A comparative study of several ADPCM schemes with linear and nonlinear prediction—0
A comparison study of CNN denoisers on PRNU extraction—0
Show:102550
← PrevPage 138 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