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 451–500 of 4925 papers

TitleStatusHype
Adaptive Data-Free QuantizationCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference TimeCode1
Efficient-VDVAE: Less is moreCode1
Learning Architectures for Binary NetworksCode1
Learning Cross-Scale Weighted Prediction for Efficient Neural Video CompressionCode1
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense RetrievalCode1
Learning Statistical Texture for Semantic SegmentationCode1
Learning to Groove with Inverse Sequence TransformationsCode1
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
Least squares binary quantization of neural networksCode1
Efficient and Robust Quantization-aware Training via Adaptive Coreset SelectionCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
Exploiting LLM QuantizationCode1
Lightweight Super-Resolution Head for Human Pose EstimationCode1
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
EFaR 2023: Efficient Face Recognition CompetitionCode1
LLMEasyQuant: Scalable Quantization for Parallel and Distributed LLM InferenceCode1
Animation from Blur: Multi-modal Blur Decomposition with Motion GuidanceCode1
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the EdgeCode1
Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade DevicesCode1
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsCode1
Dynamic Network Quantization for Efficient Video InferenceCode1
Adapting LLaMA Decoder to Vision TransformerCode1
"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel ApproachCode1
EasyQuant: Post-training Quantization via Scale OptimizationCode1
DVD-Quant: Data-free Video Diffusion Transformers QuantizationCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital FossaCode1
Machine Unlearning of Federated ClustersCode1
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Catastrophic Failure of LLM Unlearning via QuantizationCode1
BAFFLE: A Baseline of Backpropagation-Free Federated LearningCode1
Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech TranslationCode1
Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense RetrievalCode1
Matrix Compression via Randomized Low Rank and Low Precision FactorizationCode1
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D DetectionCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
AdANNS: A Framework for Adaptive Semantic SearchCode1
DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip TrainingCode1
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation SmoothingCode1
MetaQuant: Learning to Quantize by Learning to Penetrate Non-differentiable QuantizationCode1
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm QuantizerCode1
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical StudyCode1
Mind the Gap: A Practical Attack on GGUF QuantizationCode1
Mini-GPTs: Efficient Large Language Models through Contextual PruningCode1
Mixed-Precision Neural Network Quantization via Learned Layer-wise ImportanceCode1
Disentanglement via Latent QuantizationCode1
Show:102550
← PrevPage 10 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