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 3801–3850 of 4925 papers

TitleStatusHype
Patch-wise Mixed-Precision Quantization of Vision Transformer—0
A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations—0
Pathology Image Compression with Pre-trained Autoencoders—0
PathVQ: Reforming Computational Pathology Foundation Model for Whole Slide Image Analysis via Vector Quantization—0
PCDVQ: Enhancing Vector Quantization for Large Language Models via Polar Coordinate Decoupling—0
PECAN: A Product-Quantized Content Addressable Memory Network—0
Perceptual Video Quality Prediction Emphasizing Chroma Distortions—0
Performance Analysis of IRS-Assisted Cell-Free Communication—0
Performance Analysis of Massive MIMO Multi-Way Relay Networks with Low-Resolution ADCs—0
Performance Guaranteed Network Acceleration via High-Order Residual Quantization—0
Performance of Cell-Free MmWave Massive MIMO Systems with Fronthaul Compression and DAC Quantization—0
Performance Optimization for Variable Bitwidth Federated Learning in Wireless Networks—0
Persistence Codebooks for Topological Data Analysis—0
Personalized Federated Learning for Cellular VR: Online Learning and Dynamic Caching—0
Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm—0
Phoenix: A Low-Precision Floating-Point Quantization Oriented Architecture for Convolutional Neural Networks—0
Physics-aware Differentiable Discrete Codesign for Diffractive Optical Neural Networks—0
Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws—0
Pieces of Eight: 8-bit Neural Machine Translation—0
PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks—0
Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder—0
PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram—0
PIM-QAT: Neural Network Quantization for Processing-In-Memory (PIM) Systems—0
Pinball Loss Minimization for One-bit Compressive Sensing: Convex Models and Algorithms—0
Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning—0
PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions—0
PIVQGAN: Posture and Identity Disentangled Image-to-Image Translation via Vector Quantization—0
Pixel Embedding: Fully Quantized Convolutional Neural Network with Differentiable Lookup Table—0
Pixel precise unsupervised detection of viral particle proliferation in cellular imaging data—0
PKLot-A robust dataset for parking lot classification—0
Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models—0
PoET-BiN: Power Efficient Tiny Binary Neurons—0
PoGO: A Scalable Proof of Useful Work via Quantized Gradient Descent and Merkle Proofs—0
Asynchronous Decentralized SGD with Quantized and Local Updates—0
Positional Information is All You Need: A Novel Pipeline for Self-Supervised SVDE from Videos—0
Poster: Self-Supervised Quantization-Aware Knowledge Distillation—0
Posthoc Interpretation via Quantization—0
Post-Training 4-bit Quantization on Embedding Tables—0
Post-Training Non-Uniform Quantization for Convolutional Neural Networks—0
Post-Training Quantization for Cross-Platform Learned Image Compression—0
Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping—0
Post-Training Quantization for Energy Efficient Realization of Deep Neural Networks—0
Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric—0
Post-Training Quantization for Video Matting—0
Post-Training Quantization for Vision Transformer—0
Post-Training Quantization for Vision Mamba with k-Scaled Quantization and Reparameterization—0
Post-Training Quantization Is All You Need to Perform Cross-Platform Learned Image Compression—0
Shedding the Bits: Pushing the Boundaries of Quantization with Minifloats on FPGAs—0
Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision—0
Post-Training Weighted Quantization of Neural Networks for Language Models—0
Show:102550
← PrevPage 77 of 99Next →
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