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 4251–4300 of 4925 papers

TitleStatusHype
Tiny Reinforcement Learning for Quadruped Locomotion using Decision TransformersCode0
FEDZIP: A Compression Framework for Communication-Efficient Federated LearningCode0
Distilling the Knowledge of Romanian BERTs Using Multiple TeachersCode0
Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data HeterogeneityCode0
Model Compression Techniques in Biometrics Applications: A SurveyCode0
Model compression via distillation and quantizationCode0
Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain--Machine InterfacesCode0
FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going BeyondCode0
Rotation Invariant Quantization for Model CompressionCode0
QPyTorch: A Low-Precision Arithmetic Simulation FrameworkCode0
Federated Learning via Plurality VoteCode0
Mixed Non-linear Quantization for Vision TransformersCode0
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation RegularizationCode0
Routing-Guided Learned Product Quantization for Graph-Based Approximate Nearest Neighbor SearchCode0
Stealthy Backdoors as Compression ArtifactsCode0
Modulated Diffusion: Accelerating Generative Modeling with Modulated QuantizationCode0
Distillation Improves Visual Place Recognition for Low Quality ImagesCode0
Modular Quantization-Aware Training for 6D Object Pose EstimationCode0
Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMsCode0
Federated learning compression designed for lightweight communicationsCode0
Compressed Object DetectionCode0
Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text AttacksCode0
Disentanglement with Factor Quantized Variational AutoencodersCode0
Q-S5: Towards Quantized State Space ModelsCode0
Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum InferenceCode0
Accelerating PoT Quantization on Edge DevicesCode0
Federated Classification in Hyperbolic Spaces via Secure Aggregation of Convex HullsCode0
QSGD: Communication-Efficient SGD via Gradient Quantization and EncodingCode0
StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth PredictionCode0
MorpheusNet: Resource efficient sleep stage classifier for embedded on-line systemsCode0
TinySubNets: An efficient and low capacity continual learning strategyCode0
Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural NetworksCode0
MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete DiffusionCode0
AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned QuantizationCode0
Mirror Descent View for Neural Network QuantizationCode0
MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural NetworksCode0
Minimize Quantization Output Error with Bias CompensationCode0
Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local ComputationsCode0
Minimal Random Code Learning: Getting Bits Back from Compressed Model ParametersCode0
TreeLUT: An Efficient Alternative to Deep Neural Networks for Inference Acceleration Using Gradient Boosted Decision TreesCode0
MetaAug: Meta-Data Augmentation for Post-Training QuantizationCode0
BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized WeightsCode0
Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety AlignmentCode0
Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial ExamplesCode0
FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal RetrievalCode0
AMED: Automatic Mixed-Precision Quantization for Edge DevicesCode0
Discrete representations in neural models of spoken languageCode0
QTTNet: Quantized Tensor Train Neural Networks for 3D Object and Video Recognition.Code0
GLAD: Improving Latent Graph Generative Modeling with Simple QuantizationCode0
Discrete Factorization Machines for Fast Feature-based RecommendationCode0
Show:102550
← PrevPage 86 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