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 1101–1150 of 4925 papers

TitleStatusHype
Lipschitz Continuity Retained Binary Neural NetworkCode0
LISA: Learning Interpretable Skill Abstractions from LanguageCode0
LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and QuantizationCode0
Characteristics of networks generated by kernel growing neural gasCode0
Linearly Converging Error Compensated SGDCode0
Adaptive Prediction-Powered AutoEval with Reliability and Efficiency GuaranteesCode0
Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge NodesCode0
Lightweight Client-Side Chinese/Japanese Morphological Analyzer Based on Online LearningCode0
Lightweight Deep Learning Based Channel Estimation for Extremely Large-Scale Massive MIMO SystemsCode0
Light Multi-segment Activation for Model CompressionCode0
Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systemsCode0
Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy EnvironmentsCode0
An Underexplored Dilemma between Confidence and Calibration in Quantized Neural NetworksCode0
LegalEval-Q: A New Benchmark for The Quality Evaluation of LLM-Generated Legal TextCode0
Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone MicrocontrollerCode0
Central Similarity Quantization for Efficient Image and Video RetrievalCode0
Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI FeedbackCode0
Learning Space Partitions for Nearest Neighbor SearchCode0
Learning Physical-Layer Communication with Quantized FeedbackCode0
Learning Semantic Textual Similarity via Topic-informed Discrete Latent VariablesCode0
Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based ApproachCode0
Learning Convolutional Transforms for Lossy Point Cloud Geometry CompressionCode0
Causal-DFQ: Causality Guided Data-free Network QuantizationCode0
Cauchy-Schwarz RegularizersCode0
Large Scale Clustering with Variational EM for Gaussian Mixture ModelsCode0
Learning Frequency-Specific Quantization Scaling in VVC for Standard-Compliant Task-driven Image CodingCode0
LFZip: Lossy compression of multivariate floating-point time series data via improved predictionCode0
CAT: Compression-Aware Training for bandwidth reductionCode0
CASP: Compression of Large Multimodal Models Based on Attention SparsityCode0
An Overview of Arithmetic Adaptations for Inference of Convolutional Neural Networks on Re-configurable HardwareCode0
Cartesian K-MeansCode0
Adaptive Loss-aware Quantization for Multi-bit NetworksCode0
Learning Bag-of-Features Pooling for Deep Convolutional Neural NetworksCode0
Learning Accurate Performance Predictors for Ultrafast Automated Model CompressionCode0
Accelerated Nearest Neighbor Search with Quick ADCCode0
Learning Accurate Low-Bit Deep Neural Networks with Stochastic QuantizationCode0
Learning compact binary descriptors with unsupervised deep neural networksCode0
Langevin dynamics based algorithm e-THO POULA for stochastic optimization problems with discontinuous stochastic gradientCode0
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior ModelsCode0
Learned transform compression with optimized entropy encodingCode0
Learning Compression from Limited Unlabeled DataCode0
KP2Dtiny: Quantized Neural Keypoint Detection and Description on the EdgeCode0
Just Round: Quantized Observation Spaces Enable Memory Efficient Learning of Dynamic LocomotionCode0
JPEG Inspired Deep LearningCode0
Joint Maximum Purity Forest with Application to Image Super-ResolutionCode0
BRIDLE: Generalized Self-supervised Learning with QuantizationCode0
Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural NetworksCode0
KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM InferenceCode0
Forward and Backward Information Retention for Accurate Binary Neural NetworksCode0
Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language ModelsCode0
Show:102550
← PrevPage 23 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