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

Showing 20012025 of 4925 papers

TitleStatusHype
Gradient _1 Regularization for Quantization Robustness0
Gradient-Free Neural Network Training on the Edge0
Don't Fear the Bit Flips: Optimized Coding Strategies for Binary Classification0
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training0
Domain Generalization on Efficient Acoustic Scene Classification using Residual Normalization0
Granger Causality from Quantized Measurements0
Countering Adversarial Examples: Combining Input Transformation and Noisy Training0
GranQ: Granular Zero-Shot Quantization with Channel-Wise Activation Scaling in QAT0
Graph-Based Depth Denoising & Dequantization for Point Cloud Enhancement0
Graph-Collaborated Auto-Encoder Hashing for Multi-view Binary Clustering0
BiSup: Bidirectional Quantization Error Suppression for Large Language Models0
AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training0
Greedy Selection for Heterogeneous Sensors0
Greener yet Powerful: Taming Large Code Generation Models with Quantization0
HoloFormer: Deep Compression of Pre-Trained Transforms via Unified Optimization of N:M Sparsity and Integer Quantization0
Does Video Compression Impact Tracking Accuracy?0
BiQGEMM: Matrix Multiplication with Lookup Table For Binary-Coding-based Quantized DNNs0
Gridless Angular Domain Channel Estimation for mmWave Massive MIMO System With One-Bit Quantization Via Approximate Message Passing0
Gridless Multisnapshot Variational Line Spectral Estimation from Coarsely Quantized Samples0
Group channel pruning and spatial attention distilling for object detection0
Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free0
Group Invariant Deep Representations for Image Instance Retrieval0
An Empirical Study of Low Precision Quantization for TinyML0
GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking0
Does compressing activations help model parallel training?0
Show:102550
← PrevPage 81 of 197Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1FQ-ViT (ViT-L)Top-1 Accuracy (%)85.03Unverified
2FQ-ViT (ViT-B)Top-1 Accuracy (%)83.31Unverified
3FQ-ViT (Swin-B)Top-1 Accuracy (%)82.97Unverified
4FQ-ViT (Swin-S)Top-1 Accuracy (%)82.71Unverified
5FQ-ViT (DeiT-B)Top-1 Accuracy (%)81.2Unverified
6FQ-ViT (Swin-T)Top-1 Accuracy (%)80.51Unverified
7FQ-ViT (DeiT-S)Top-1 Accuracy (%)79.17Unverified
8Xception W8A8Top-1 Accuracy (%)78.97Unverified
9ADLIK-MO-ResNet50-W4A4Top-1 Accuracy (%)77.88Unverified
10ADLIK-MO-ResNet50-W3A4Top-1 Accuracy (%)77.34Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_3MAP160,327.04Unverified
2DTQMAP0.79Unverified
#ModelMetricClaimedVerifiedStatus
1OutEffHop-Bert_basePerplexity6.3Unverified
2OutEffHop-Bert_basePerplexity6.21Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy98.13Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy92.92Unverified
#ModelMetricClaimedVerifiedStatus
1SSD ResNet50 V1 FPN 640x640MAP34.3Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-495.13Unverified
#ModelMetricClaimedVerifiedStatus
1TAR @ FAR=1e-496.38Unverified
#ModelMetricClaimedVerifiedStatus
13DCNN_VIVA_5All84,809,664Unverified
#ModelMetricClaimedVerifiedStatus
1Accuracy99.8Unverified