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 2451–2500 of 4925 papers

TitleStatusHype
Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning—0
Distributed Optimization via Gradient Descent with Event-Triggered Zooming over Quantized Communication—0
HDR Imaging With One-Bit Quantization—0
Training Acceleration of Low-Rank Decomposed Networks using Sequential Freezing and Rank Quantization—0
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models—0
Bandwidth-efficient Inference for Neural Image Compression—0
RobustEdge: Low Power Adversarial Detection for Cloud-Edge Systems—0
QuantEase: Optimization-based Quantization for Language Models—0
Compressing Vision Transformers for Low-Resource Visual LearningCode0
A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking—0
On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks—0
On the fly Deep Neural Network Optimization Control for Low-Power Computer Vision—0
Softmax Bias Correction for Quantized Generative Models—0
eDKM: An Efficient and Accurate Train-time Weight Clustering for Large Language Models—0
Learning Category Trees for ID-Based Recommendation: Exploring the Power of Differentiable Vector QuantizationCode0
Implementation and Evaluation of Physical Layer Key Generation on SDR based LoRa Platform—0
FPTQ: Fine-grained Post-Training Quantization for Large Language Models—0
Uncovering the Hidden Cost of Model CompressionCode0
Continual Learning for Generative Retrieval over Dynamic CorporaCode0
Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message PropagationCode0
On-Device Learning with Binary Neural Networks—0
MEMORY-VQ: Compression for Tractable Internet-Scale Memory—0
Maestro: Uncovering Low-Rank Structures via Trainable DecompositionCode0
A2Q: Accumulator-Aware Quantization with Guaranteed Overflow AvoidanceCode0
Efficient Learned Lossless JPEG Recompression—0
Quantized distributed Nash equilibrium seeking under DoS attacks—0
Hybrid noise shaping for audio coding using perfectly overlapped window—0
Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition—0
Consistent Signal Reconstruction from Streaming Multivariate Time Series—0
Robust open-set classification for encrypted traffic fingerprintingCode0
Distributed Energy Resource Management: All-Time Resource-Demand Feasibility, Delay-Tolerance, Nonlinearity, and Beyond—0
Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Images—0
Sampling From Autoencoders' Latent Space via Quantization And Probability Mass Function Concepts—0
QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection—0
Quantization-based Optimization with Perspective of Quantum Mechanics—0
Analyzing Quantization in TVM—0
ResQ: Residual Quantization for Video Perception—0
SHARK: A Lightweight Model Compression Approach for Large-scale Recommender Systems—0
FunQuant: A R package to perform quantization in the context of rare events and time-consuming simulations—0
JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer—0
Precision and Recall Reject Curves for Classification—0
FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs—0
Characteristics of networks generated by kernel growing neural gasCode0
AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model—0
Ternary Singular Value Decomposition as a Better Parameterized Form in Linear MappingCode0
A Survey on Model Compression for Large Language Models—0
Gradient-Based Post-Training Quantization: Challenging the Status Quo—0
Unified Data-Free Compression: Pruning and Quantization without Fine-Tuning—0
Efficient Neural PDE-Solvers using Quantization Aware Training—0
Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex HullsCode0
Show:102550
← PrevPage 50 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