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
BOMP-NAS: Bayesian Optimization Mixed Precision NAS—0
Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals—0
An improved wavelet-based signal-denoising architecture with less hardware consumption—0
Efficient Systolic Array Based on Decomposable MAC for Quantized Deep Neural Networks—0
Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction—0
Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis—0
Edge Deep Learning for Neural Implants—0
Efficient Vision-based Vehicle Speed Estimation—0
Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers—0
CBQ: Cross-Block Quantization for Large Language Models—0
Edge Computing for Physics-Driven AI in Computational MRI: A Feasibility Study—0
Ef-QuantFace: Streamlined Face Recognition with Small Data and Low-Bit Precision—0
CDQuant: Greedy Coordinate Descent for Accurate LLM Quantization—0
Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks—0
An Improved BKW Algorithm for LWE with Applications to Cryptography and Lattices—0
ELMGS: Enhancing memory and computation scaLability through coMpression for 3D Gaussian Splatting—0
Embedded Phase Shifting: Robust Phase Shifting With Embedded Signals—0
Embedding Compression for Efficient Re-Identification—0
Adaptive Block Floating-Point for Analog Deep Learning Hardware—0
Exploring Neural Networks Quantization via Layer-Wise Quantization Analysis—0
Emergent Quantized Communication—0
Emotion Recognition Using Speaker Cues—0
Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN—0
Empirical Evaluation of Post-Training Quantization Methods for Language Tasks—0
EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference—0
Edge AI: Evaluation of Model Compression Techniques for Convolutional Neural Networks—0
Emulation Learning for Neuromimetic Systems—0
Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications—0
BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch—0
Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization—0
Edge AI-Enabled Chicken Health Detection Based on Enhanced FCOS-Lite and Knowledge Distillation—0
Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruning—0
An Implementation of Vector Quantization using the Genetic Algorithm Approach—0
Enabling On-Device Medical AI Assistants via Input-Driven Saliency Adaptation—0
EDAS: Efficient and Differentiable Architecture Search—0
Adaptive Asymmetric Label-guided Hashing for Multimedia Search—0
ECG Biometric Authentication Using Self-Supervised Learning for IoT Edge Sensors—0
End-to-End Autoencoder Communications with Optimized Interference Suppression—0
BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices—0
End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs—0
End-to-End Efficient Representation Learning via Cascading Combinatorial Optimization—0
End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruning—0
APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm—0
End-to-end Keyword Spotting using Neural Architecture Search and Quantization—0
End-to-End Latent Fingerprint Search—0
End-to-End Learned Image Compression with Quantized Weights and Activations—0
Single-path Bit Sharing for Automatic Loss-aware Model Compression—0
Characterising Bias in Compressed Models—0
End-to-End Neural Network Compression via _1_2 Regularized Latency Surrogates—0
Exploring Model Invariance with Discrete Search for Ultra-Low-Bit Quantization—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