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 3001–3050 of 4925 papers

TitleStatusHype
Data-Driven Deep Learning Based Hybrid Beamforming for Aerial Massive MIMO-OFDM Systems with Implicit CSI—0
Design Space Exploration of Dense and Sparse Mapping Schemes for RRAM Architectures—0
Tk-merge: Computationally Efficient Robust Clustering Under General Assumptions—0
Improving Performance of Semantic Segmentation CycleGANs by Noise Injection into the Latent Segmentation Space—0
VAQF: Fully Automatic Software-Hardware Co-Design Framework for Low-Bit Vision Transformer—0
Neural Network Compression of ACAS Xu Early Prototype is Unsafe: Closed-Loop Verification through Quantized State BackreachabilityCode0
UWC: Unit-wise Calibration Towards Rapid Network Compression—0
Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing—0
Boosted Dense Retriever—0
UDC: Unified DNAS for Compressible TinyML Models—0
ViT2Hash: Unsupervised Information-Preserving Hashing—0
Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based RetrievalCode1
A Planck Radiation and Quantization Scheme for Human Cognition and Language—0
A Physics-Informed Vector Quantized Autoencoder for Data Compression of Turbulent FlowCode0
Bandlimited signal reconstruction from leaky integrate-and-fire encoding using POCS—0
An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic—0
PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++Code1
High-contrast, speckle-free, true 3D holography via binary CGH optimization—0
Video Coding for Machines: Partial transmission of SIFT features—0
Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion TheoryCode0
Detection of extragalactic Ultra-Compact Dwarfs and Globular Clusters using Explainable AI techniquesCode0
A Robust Visual Sampling Model Inspired by Receptive Field—0
Elastic Product Quantization for Time SeriesCode0
IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion—0
Quantization-Aware Deep Optics for Diffractive Snapshot Hyperspectral Imaging—0
Channel Balancing for Accurate Quantization of Winograd Convolutions—0
Improving Robustness Against Stealthy Weight Bit-Flip Attacks by Output Code MatchingCode0
Instance-Aware Dynamic Neural Network QuantizationCode0
Data-Free Network Compression via Parametric Non-Uniform Mixed Precision Quantization—0
Learnable Lookup Table for Neural Network QuantizationCode1
Mutual Quantization for Cross-Modal Search With Noisy Labels—0
AlignQ: Alignment Quantization With ADMM-Based Correlation PreservationCode1
Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error—0
RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks—0
SceneSqueezer: Learning To Compress Scene for Camera Relocalization—0
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
Croesus: Multi-Stage Processing and Transactions for Video-Analytics in Edge-Cloud Systems—0
Studying the Interplay between Information Loss and Operation Loss in Representations for Classification—0
Finding the Task-Optimal Low-Bit Sub-Distribution in Deep Neural NetworksCode1
Automatic Mixed-Precision Quantization Search of BERT—0
End-to-End Autoencoder Communications with Optimized Interference Suppression—0
HiKonv: High Throughput Quantized Convolution With Novel Bit-wise Management and Computation—0
Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction—0
Learning Cross-Scale Weighted Prediction for Efficient Neural Video CompressionCode1
BMPQ: Bit-Gradient Sensitivity Driven Mixed-Precision Quantization of DNNs from Scratch—0
Stochastic Learning Equation using Monotone Increasing Resolution of Quantization—0
Training Quantized Deep Neural Networks via Cooperative CoevolutionCode1
Distilling the Knowledge of Romanian BERTs Using Multiple TeachersCode0
Manifold learning via quantum dynamics—0
Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats—0
Show:102550
← PrevPage 61 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