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 4451–4500 of 4925 papers

TitleStatusHype
Adaptive Loss-aware Quantization for Multi-bit NetworksCode0
Self-Supervised Learning for Color Spike Camera ReconstructionCode0
Quantized Fisher Discriminant AnalysisCode0
OLALa: Online Learned Adaptive Lattice Codes for Heterogeneous Federated LearningCode0
Quantized Fourier and Polynomial Features for more Expressive Tensor Network ModelsCode0
Lipschitz Continuity Retained Binary Neural NetworkCode0
Linearly Converging Error Compensated SGDCode0
Self-supervised Pre-training of Text RecognizersCode0
Explaining Reject Options of Learning Vector Quantization ClassifiersCode0
Self-supervised Product Quantization for Deep Unsupervised Image RetrievalCode0
Deep Triplet QuantizationCode0
Deep Task-Based Analog-to-Digital ConversionCode0
Lightweight Deep Learning Based Channel Estimation for Extremely Large-Scale Massive MIMO SystemsCode0
Compositional Sketch SearchCode0
Two-Step Quantization for Low-Bit Neural NetworksCode0
Composite QuantizationCode0
On-Device Language Models: A Comprehensive ReviewCode0
Communication Efficient Private Federated Learning Using DitheringCode0
On-Device LLM for Context-Aware Wi-Fi RoamingCode0
Communication-Efficient Multi-Device Inference Acceleration for Transformer ModelsCode0
Lightweight Client-Side Chinese/Japanese Morphological Analyzer Based on Online LearningCode0
DeepShift: Towards Multiplication-Less Neural NetworksCode0
Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN InferenceCode0
Bag of Tricks for Optimizing Transformer EfficiencyCode0
Towards Efficient Verification of Quantized Neural NetworksCode0
Deep reverse tone mappingCode0
Autoregressive Co-Training for Learning Discrete Speech RepresentationsCode0
Quantized Prompt for Efficient Generalization of Vision-Language ModelsCode0
A Binary Variational Autoencoder for HashingCode0
An Information-Theoretic Analysis of Self-supervised Discrete Representations of SpeechCode0
Semi-supervised 3D Object Detection with PatchTeacher and PillarMixCode0
Adaptive Computation Modules: Granular Conditional Computation For Efficient InferenceCode0
Light Multi-segment Activation for Model CompressionCode0
QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement LearningCode0
Communication-Efficient Federated Learning via Predictive CodingCode0
Algorithm and VLSI Design for 1-bit Data Detection in Massive MIMO-OFDMCode0
LiFT: Lightweight, FPGA-tailored 3D object detection based on LiDAR dataCode0
LFZip: Lossy compression of multivariate floating-point time series data via improved predictionCode0
Expansion Quantization Network: An Efficient Micro-emotion Annotation and Detection FrameworkCode0
Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation AnalysisCode0
ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range ContentCode0
SYQ: Learning Symmetric Quantization For Efficient Deep Neural NetworksCode0
One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language ModelsCode0
One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization TrainingCode0
EXAQ: Exponent Aware Quantization For LLMs AccelerationCode0
Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy EnvironmentsCode0
Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI FeedbackCode0
An exploration of the effect of quantisation on energy consumption and inference time of StarCoder2Code0
Towards Highly Accurate and Stable Face Alignment for High-Resolution VideosCode0
Vision-Language and Large Language Model Performance in Gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and Quantized ModelsCode0
Show:102550
← PrevPage 90 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