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 2251–2300 of 4925 papers

TitleStatusHype
A Cost-Efficient FPGA Implementation of Tiny Transformer Model using Neural ODE—0
Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation—0
Model-Free Learning for the Linear Quadratic Regulator over Rate-Limited Channels—0
General Point Model Pretraining with Autoencoding and AutoregressiveCode0
Are Conventional SNNs Really Efficient? A Perspective from Network Quantization—0
Reg-PTQ: Regression-specialized Post-training Quantization for Fully Quantized Object Detector—0
Enhancing Post-training Quantization Calibration through Contrastive Learning—0
PredToken: Predicting Unknown Tokens and Beyond with Coarse-to-Fine Iterative Decoding—0
PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks—0
Data-Free Quantization via Pseudo-label Filtering—0
HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes—0
Compact Neural Graphics Primitives with Learned Hash Probing—0
FALCON: Feature-Label Constrained Graph Net Collapse for Memory Efficient GNNsCode0
A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization—0
Efficient Asynchronous Federated Learning with Sparsification and Quantization—0
Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization—0
Cross-Layer Optimization for Fault-Tolerant Deep Learning—0
Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data HeterogeneityCode0
Towards Efficient Verification of Quantized Neural NetworksCode0
Find the Lady: Permutation and Re-Synchronization of Deep Neural NetworksCode0
SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search—0
Power-Efficient Sampling—0
Quantized Decoder in Learned Image Compression for Deterministic Reconstruction—0
Post-Training Quantization for Re-parameterization via Coarse & Fine Weight SplittingCode0
SPT: Fine-Tuning Transformer-based Language Models Efficiently with SparsificationCode0
IQNet: Image Quality Assessment Guided Just Noticeable Difference Prefiltering For Versatile Video Coding—0
Adaptive Computation Modules: Granular Conditional Computation For Efficient InferenceCode0
Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition—0
USM-Lite: Quantization and Sparsity Aware Fine-tuning for Speech Recognition with Universal Speech Models—0
CBQ: Cross-Block Quantization for Large Language Models—0
When Bio-Inspired Computing meets Deep Learning: Low-Latency, Accurate, & Energy-Efficient Spiking Neural Networks from Artificial Neural Networks—0
Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization—0
IDKM: Memory Efficient Neural Network Quantization via Implicit, Differentiable k-Means—0
Decoupling Meta-Reinforcement Learning with Gaussian Task Contexts and SkillsCode0
FP8-BERT: Post-Training Quantization for Transformer—0
QMGeo: Differentially Private Federated Learning via Stochastic Quantization with Mixed Truncated Geometric Distribution—0
Neural Architecture Codesign for Fast Bragg Peak Analysis—0
Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the EdgeCode0
Efficient Quantization Strategies for Latent Diffusion Models—0
Automotive Radar Sensing with Sparse Linear Arrays Using One-Bit Hankel Matrix Completion—0
Understanding the Effect of Model Compression on Social Bias in Large Language ModelsCode0
An Experimental Study: Assessing the Combined Framework of WavLM and BEST-RQ for Text-to-Speech Synthesis—0
GenQ: Quantization in Low Data Regimes with Generative Synthetic DataCode0
Rate-splitting Multiple Access for Hierarchical HAP-LAP Networks under Limited Fronthaul—0
Enhancing Kinship Verification through Multiscale Retinex and Combined Deep-Shallow features—0
All Rivers Run to the Sea: Private Learning with Asymmetric Flows—0
Unified learning-based lossy and lossless JPEG recompression—0
PLUM: Improving Inference Efficiency By Leveraging Repetition-Sparsity Trade-OffCode0
Low-Precision Mixed-Computation Models for Inference on Edge—0
QuantAttack: Exploiting Dynamic Quantization to Attack Vision TransformersCode0
Show:102550
← PrevPage 46 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