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 751–800 of 4925 papers

TitleStatusHype
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D DetectionCode1
NVTC: Nonlinear Vector Transform CodingCode1
F8Net: Fixed-Point 8-bit Only Multiplication for Network QuantizationCode1
OMPQ: Orthogonal Mixed Precision QuantizationCode1
Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN TrainingCode1
DiTAS: Quantizing Diffusion Transformers via Enhanced Activation SmoothingCode1
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network QuantizationCode1
One Loss for Quantization: Deep Hashing with Discrete Wasserstein Distributional MatchingCode1
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution NetworksCode1
Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural NetworksCode1
Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense EmbeddingsCode1
Optimal Target Shape for LiDAR Pose EstimationCode1
Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and DistillationCode1
Distributed Learning Systems with First-order MethodsCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Channel Estimation for Quantized Systems based on Conditionally Gaussian Latent ModelsCode1
Mixed Precision DNNs: All you need is a good parametrizationCode1
Algorithm-hardware Co-design for Deformable ConvolutionCode1
Differentiable JPEG: The Devil is in the DetailsCode1
Clustering the Sketch: A Novel Approach to Embedding Table CompressionCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
PAMS: Quantized Super-Resolution via Parameterized Max ScaleCode1
Disentanglement via Latent QuantizationCode1
DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip TrainingCode1
PD-Quant: Post-Training Quantization based on Prediction Difference MetricCode1
PeQuENet: Perceptual Quality Enhancement of Compressed Video with Adaptation- and Attention-based NetworkCode1
Design Methodology for Deep Out-of-Distribution Detectors in Real-Time Cyber-Physical SystemsCode1
Phrase Retrieval Learns Passage Retrieval, TooCode1
Device-Robust Acoustic Scene Classification Based on Two-Stage Categorization and Data AugmentationCode1
PolyFormer: Referring Image Segmentation as Sequential Polygon GenerationCode1
PoseGPT: Quantization-based 3D Human Motion Generation and ForecastingCode1
Position-based Scaled Gradient for Model Quantization and PruningCode1
Deep Transferring QuantizationCode1
DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two QuantizationCode1
DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined RotationCode1
CISSIR: Beam Codebooks with Self-Interference Reduction Guarantees for Integrated Sensing and Communication Beyond 5GCode1
Deep Geometry Post-Processing for Decompressed Point CloudsCode1
APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor CoresCode1
PRISE: LLM-Style Sequence Compression for Learning Temporal Action Abstractions in ControlCode1
Privacy-Preserving Action Recognition via Motion Difference QuantizationCode1
Deep Learning-Enabled One-Bit DoA EstimationCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
Proximal Mean-field for Neural Network QuantizationCode1
Pruning Large Language Models with Semi-Structural Adaptive Sparse TrainingCode1
Dataset Quantization with Active Learning based Adaptive SamplingCode1
PSAQ-ViT V2: Towards Accurate and General Data-Free Quantization for Vision TransformersCode1
DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector QuantizationCode1
PTQ4DiT: Post-training Quantization for Diffusion TransformersCode1
Deep PeNSieve: A deep learning framework based on the posit number systemCode1
DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion ModelsCode1
Show:102550
← PrevPage 16 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