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 2101–2150 of 4925 papers

TitleStatusHype
MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language ModelsCode1
Grounded Object Centric Learning—0
Low bit rate binaural link for improved ultra low-latency low-complexity multichannel speech enhancement in Hearing Aids—0
Extreme Image Compression using Fine-tuned VQGANs—0
A Survey of Techniques for Optimizing Transformer Inference—0
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical StudyCode1
Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models—0
Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression—0
Mixed-Precision Quantization for Deep Vision Models with Integer Quadratic ProgrammingCode0
Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles—0
InfLoR-SNN: Reducing Information Loss for Spiking Neural Networks—0
QBitOpt: Fast and Accurate Bitwidth Reallocation during Training—0
Q-YOLOP: Quantization-aware You Only Look Once for Panoptic Driving Perception—0
Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectives—0
KP2Dtiny: Quantized Neural Keypoint Detection and Description on the EdgeCode0
INT-FP-QSim: Mixed Precision and Formats For Large Language Models and Vision TransformersCode1
ITA: An Energy-Efficient Attention and Softmax Accelerator for Quantized Transformers—0
Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge—0
Dequantization and Color Transfer with Diffusion ModelsCode0
Pruning vs Quantization: Which is Better?Code1
Fast Private Kernel Density Estimation via Locality Sensitive QuantizationCode0
Greedy Selection for Heterogeneous Sensors—0
Line Spectrum Estimation and Detection with Few-bit ADCs: Theoretical Analysis and Generalized NOMP Algorithm—0
Data-Free Quantization via Mixed-Precision Compensation without Fine-Tuning—0
Q-YOLO: Efficient Inference for Real-time Object Detection—0
On a Relation Between the Rate-Distortion Function and Optimal Transport—0
Quantization Variation: A New Perspective on Training Transformers with Low-Bit PrecisionCode1
Analysis of the influence of final resolution on ADC accuracy—0
Unlimited Sampling Radar: a Real-Time End-to-End Demonstrator—0
ReLU Neural Networks, Polyhedral Decompositions, and Persistent Homolog—0
Analysis of Oversampling in Uplink Massive MIMO-OFDM with Low-Resolution ADCs—0
Designing strong baselines for ternary neural network quantization through support and mass equalization—0
A Structurally Regularized CNN Architecture via Adaptive Subband Decomposition—0
Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural RepresentationCode0
DNA-TEQ: An Adaptive Exponential Quantization of Tensors for DNN Inference—0
MotionGPT: Human Motion as a Foreign LanguageCode3
Efficient High-Resolution Template Matching with Vector Quantized Nearest Neighbour FieldsCode0
Partitioning-Guided K-Means: Extreme Empty Cluster Resolution for Extreme Model Compression—0
INR-MDSQC: Implicit Neural Representation Multiple Description Scalar Quantization for robust image Coding—0
QNNRepair: Quantized Neural Network Repair—0
Quantizable Transformers: Removing Outliers by Helping Attention Heads Do NothingCode1
Image storage on synthetic DNA using compressive autoencoders and DNA-adapted entropy coders—0
Subgraph Stationary Hardware-Software Inference Co-Design—0
An efficient and straightforward online quantization method for a data stream through remove-birth updatingCode0
Beyond Learned Metadata-based Raw Image ReconstructionCode1
Randomized Quantization is All You Need for Differential Privacy in Federated LearningCode0
DynaQuant: Compressing Deep Learning Training Checkpoints via Dynamic Quantization—0
Low-complexity Multidimensional DCT Approximations—0
Pushing the Limits of 3D Shape Generation at Scale—0
Dynamic Cell Modeling of Li-Ion Polymer Batteries for Precise SOC Estimation in Power-Needy Autonomous Electric Vehicles—0
Show:102550
← PrevPage 43 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