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 2601–2650 of 4925 papers

TitleStatusHype
Implementation of a framework for deploying AI inference engines in FPGAs—0
Low Precision Quantization-aware Training in Spiking Neural Networks with Differentiable Quantization Function—0
Intriguing Properties of Quantization at Scale—0
Stochastic Gradient Langevin Dynamics Based on Quantization with Increasing Resolution—0
DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes—0
Global-QSGD: Practical Floatless Quantization for Distributed Learning with Theoretical Guarantees—0
Reducing Communication for Split Learning by Randomized Top-k Sparsification—0
BRICS: Bi-level feature Representation of Image CollectionS—0
SlimFit: Memory-Efficient Fine-Tuning of Transformer-based Models Using Training Dynamics—0
Reversible Quantization Index Modulation for Static Deep Neural Network Watermarking—0
A Transfer Learning and Explainable Solution to Detect mpox from Smartphones imagesCode0
Efficient Storage of Fine-Tuned Models via Low-Rank Approximation of Weight Residuals—0
Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing—0
2-bit Conformer quantization for automatic speech recognition—0
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time—0
PQA: Exploring the Potential of Product Quantization in DNN Hardware AccelerationCode0
BinaryViT: Towards Efficient and Accurate Binary Vision Transformers—0
Just CHOP: Embarrassingly Simple LLM Compression—0
RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models—0
Downlink Clustering-Based Scheduling of IRS-Assisted Communications With Reconfiguration Constraints—0
Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization—0
Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML—0
Adversarial Defenses via Vector Quantization—0
Differential Privacy with Random Projections and Sign Random Projections—0
TSPTQ-ViT: Two-scaled post-training quantization for vision transformer—0
Digital-SC: Digital Semantic Communication with Adaptive Network Split and Learned Non-Linear Quantization—0
TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers—0
Revisiting Data Augmentation in Model Compression: An Empirical and Comprehensive Study—0
Bi-ViT: Pushing the Limit of Vision Transformer Quantization—0
FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization—0
Integer or Floating Point? New Outlooks for Low-Bit Quantization on Large Language Models—0
Atomic Anatomy of Low-Inertia Power Systems—0
ReTAG: Reasoning Aware Table to Analytic Text Generation—0
Two-Bit RIS-Aided Communications at 3.5GHz: Some Insights from the Measurement Results Under Multiple Practical Scenes—0
Boost Vision Transformer with GPU-Friendly Sparsity and Quantization—0
DQ-Whisper: Joint Distillation and Quantization for Efficient Multilingual Speech Recognition—0
Q-SHED: Distributed Optimization at the Edge via Hessian Eigenvectors Quantization—0
Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt—0
Component Training of Turbo Autoencoders—0
MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural NetworksCode0
Task-Oriented Communication Design at Scale—0
Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks—0
Fast Inference of Tree Ensembles on ARM Devices—0
Designing Discontinuities—0
Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling—0
Analyzing Compression Techniques for Computer Vision—0
Quantization in Spiking Neural NetworksCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
Accelerator-Aware Training for Transducer-Based Speech Recognition—0
Speaker Diaphragm Excursion Prediction: deep attention and online adaptation—0
Show:102550
← PrevPage 53 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