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 601–650 of 4925 papers

TitleStatusHype
PoseGPT: Quantization-based 3D Human Motion Generation and ForecastingCode1
Q-ViT: Accurate and Fully Quantized Low-bit Vision TransformerCode1
Clustering the Sketch: A Novel Approach to Embedding Table CompressionCode1
Hybrid Inverted Index Is a Robust Accelerator for Dense RetrievalCode1
Set2Box: Similarity Preserving Representation Learning of SetsCode1
Active Image IndexingCode1
Outlier Suppression: Pushing the Limit of Low-bit Transformer Language ModelsCode1
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision TransformersCode1
Generative Adversarial Super-Resolution at the Edge with Knowledge DistillationCode1
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network QuantizationCode1
Lossy Image Compression with Quantized Hierarchical VAEsCode1
Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and PruningCode1
Fast Nearest Convolution for Real-Time Efficient Image Super-ResolutionCode1
Joint Privacy Enhancement and Quantization in Federated LearningCode1
DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two QuantizationCode1
FP8 Quantization: The Power of the ExponentCode1
Keyword Spotting System and Evaluation of Pruning and Quantization Methods on Low-power Edge MicrocontrollersCode1
Privacy-Preserving Action Recognition via Motion Difference QuantizationCode1
PalQuant: Accelerating High-precision Networks on Low-precision AcceleratorsCode1
Design Methodology for Deep Out-of-Distribution Detectors in Real-Time Cyber-Physical SystemsCode1
CrAM: A Compression-Aware MinimizerCode1
Reconciling Security and Communication Efficiency in Federated LearningCode1
CADyQ: Content-Aware Dynamic Quantization for Image Super-ResolutionCode1
Animation from Blur: Multi-modal Blur Decomposition with Motion GuidanceCode1
Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning ApproachCode1
CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in SpaceCode1
Synergistic Self-supervised and Quantization LearningCode1
Network Binarization via Contrastive LearningCode1
BL-JUNIPER: A CNN-Assisted Framework for Perceptual Video Coding Leveraging Block-Level JNDCode1
QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit QuantizationCode1
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language ModelsCode1
Seizure Detection and Prediction by Parallel Memristive Convolutional Neural NetworksCode1
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated LearningCode1
Lossy Compression with Gaussian DiffusionCode1
Fast Lossless Neural Compression with Integer-Only Discrete FlowsCode1
PeQuENet: Perceptual Quality Enhancement of Compressed Video with Adaptation- and Attention-based NetworkCode1
QONNX: Representing Arbitrary-Precision Quantized Neural NetworksCode1
Federated Optimization Algorithms with Random Reshuffling and Gradient CompressionCode1
Variable-rate hierarchical CPC leads to acoustic unit discovery in speechCode1
NIPQ: Noise proxy-based Integrated Pseudo-QuantizationCode1
One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional MatchingCode1
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial LearningCode1
Wavelet Feature Maps Compression for Image-to-Image CNNsCode1
Vector-Quantized Input-Contextualized Soft Prompts for Natural Language UnderstandingCode1
Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense RetrievalCode1
SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic QuantizationCode1
Reduce Information Loss in Transformers for Pluralistic Image InpaintingCode1
Communication-Efficient Adaptive Federated LearningCode1
Deep Geometry Post-Processing for Decompressed Point CloudsCode1
Show:102550
← PrevPage 13 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