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 4851–4900 of 4925 papers

TitleStatusHype
Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial PruningCode0
PsyLite Technical ReportCode0
Guetzli: Perceptually Guided JPEG EncoderCode0
DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth GradientsCode0
GT-SVQ: A Linear-Time Graph Transformer for Node Classification Using Spiking Vector QuantizationCode0
PTQ4RIS: Post-Training Quantization for Referring Image SegmentationCode0
GSB: Group Superposition Binarization for Vision Transformer with Limited Training SamplesCode0
GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing UnitsCode0
GQFedWAvg: Optimization-Based Quantized Federated Learning in General Edge Computing SystemsCode0
Goten: GPU-Outsourcing Trusted Execution of Neural Network Training and PredictionCode0
Don't take it lightly: Phasing optical random projections with unknown operatorsCode0
The ZipML Framework for Training Models with End-to-End Low Precision: The Cans, the Cannots, and a Little Bit of Deep LearningCode0
Pufferfish: Communication-efficient Models At No Extra CostCode0
PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-DiscriminatorsCode0
PULP-NN: Accelerating Quantized Neural Networks on Parallel Ultra-Low-Power RISC-V ProcessorsCode0
RNN-SM: Fast Steganalysis of VoIP Streams Using Recurrent Neural NetworkCode0
Content-Aware Radiance Fields: Aligning Model Complexity with Scene Intricacy Through Learned Bitwidth QuantizationCode0
Robust and Communication-Efficient Collaborative LearningCode0
Thinking in Granularity: Dynamic Quantization for Image Super-Resolution by Intriguing Multi-Granularity CluesCode0
Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache CompressionCode0
Robust Clustering on High-Dimensional Data with Stochastic QuantizationCode0
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMsCode0
Conformalized High-Density Quantile Regression via Dynamic Prototypes-based Probability Density EstimationCode0
Approximate Message Passing with Parameter Estimation for Heavily Quantized MeasurementsCode0
Genie: Show Me the Data for QuantizationCode0
General Point Model Pretraining with Autoencoding and AutoregressiveCode0
Conditional Probability Models for Deep Image CompressionCode0
Applying generative neural networks for fast simulations of the ALICE (CERN) experimentCode0
Computational data analysis for first quantization estimation on JPEG double compressed imagesCode0
Compressing Word Embeddings via Deep Compositional Code LearningCode0
Generalized Relevance Learning Grassmann QuantizationCode0
Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer GateCode0
Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional ComputingCode0
Robustness Analysis of Deep Learning Frameworks on Mobile PlatformsCode0
GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language ModelsCode0
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural ArchitectureCode0
FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-designCode0
FP4DiT: Towards Effective Floating Point Quantization for Diffusion TransformersCode0
Compressing Vision Transformers for Low-Resource Visual LearningCode0
Does quantization affect models' performance on long-context tasks?Code0
Dequantization and Color Transfer with Diffusion ModelsCode0
Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal BalanceCode0
Foundations of Large Language Model Compression -- Part 1: Weight QuantizationCode0
Robustness of Generalized Learning Vector Quantization Models against Adversarial AttacksCode0
Q&C: When Quantization Meets Cache in Efficient Image GenerationCode0
ACCEPT: Adaptive Codebook for Composite and Efficient Prompt TuningCode0
FLoCoRA: Federated learning compression with low-rank adaptationCode0
Floating-Point Quantization Analysis of Multi-Layer Perceptron Artificial Neural NetworksCode0
FlexRound: Learnable Rounding based on Element-wise Division for Post-Training QuantizationCode0
Flexible Mixed Precision Quantization for Learned Image CompressionCode0
Show:102550
← PrevPage 98 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