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 1501–1550 of 4925 papers

TitleStatusHype
A Novel Audio Representation for Music Genre Identification in MIR—0
BiPer: Binary Neural Networks using a Periodic FunctionCode1
Instance-Aware Group Quantization for Vision Transformers—0
Transformer based Pluralistic Image Completion with Reduced Information LossCode2
Towards Variable and Coordinated Holistic Co-Speech Motion Generation—0
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMsCode1
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs—0
Accurate Block Quantization in LLMs with Outliers—0
Genetic Quantization-Aware Approximation for Non-Linear Operations in TransformersCode1
Within the Dynamic Context: Inertia-aware 3D Human Modeling with Pose Sequence—0
Uncertainty-Aware Deep Video Compression with Ensembles—0
Meta-Heuristic Fronthaul Bit Allocation for Cell-free Massive MIMO Systems—0
QNCD: Quantization Noise Correction for Diffusion ModelsCode0
Oh! We Freeze: Improving Quantized Knowledge Distillation via Signal Propagation Analysis for Large Language Models—0
The Unreasonable Ineffectiveness of the Deeper LayersCode3
Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN—0
Work in Progress: Linear Transformers for TinyML—0
GLAD: Improving Latent Graph Generative Modeling with Simple QuantizationCode0
Neural Image Compression with Quantization Rectifier—0
On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model PerformanceCode0
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative ModelsCode0
SignSGD with Federated VotingCode0
Magic for the Age of Quantized DNNs—0
Infrastructure-Assisted Collaborative Perception in Automated Valet Parking: A Safety Perspective—0
HAC: Hash-grid Assisted Context for 3D Gaussian Splatting CompressionCode3
NoisyDECOLLE: Robust Local Learning for SNNs on Neuromorphic HardwareCode0
Provable Privacy with Non-Private Pre-Processing—0
Super-High-Fidelity Image Compression via Hierarchical-ROI and Adaptive Quantization—0
AffineQuant: Affine Transformation Quantization for Large Language ModelsCode1
Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block QuantizationCode2
MELTing point: Mobile Evaluation of Language TransformersCode1
Floating-Point Quantization Analysis of Multi-Layer Perceptron Artificial Neural NetworksCode0
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression—0
Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance—0
HyperVQ: MLR-based Vector Quantization in Hyperbolic Space—0
Hierarchical Frequency-based Upsampling and Refining for Compressed Video Quality Enhancement—0
Self-Supervised Quantization-Aware Knowledge DistillationCode1
Representing Domain-Mixing Optical Degradation for Real-World Computational Aberration Correction via Vector QuantizationCode1
Quantization Effects on Neural Networks Perception: How would quantization change the perceptual field of vision models?Code0
Quantization Avoids Saddle Points in Distributed Optimization—0
BRIEDGE: EEG-Adaptive Edge AI for Multi-Brain to Multi-Robot Interaction—0
CRB Analysis for Mixed-ADC Based DOA Estimation—0
FedComLoc: Communication-Efficient Distributed Training of Sparse and Quantized Models—0
Generalized Relevance Learning Grassmann QuantizationCode0
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and EfficiencyCode0
CLIP-EBC: CLIP Can Count Accurately through Enhanced Blockwise ClassificationCode2
UniCode: Learning a Unified Codebook for Multimodal Large Language Models—0
TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic TasksCode1
Collaborative Automotive Radar Sensing via Mixed-Precision Distributed Array Completion—0
Strategizing against Q-learners: A Control-theoretical Approach—0
Show:102550
← PrevPage 31 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