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 501–550 of 4925 papers

TitleStatusHype
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANNCode1
Fast Nearest Convolution for Real-Time Efficient Image Super-ResolutionCode1
Real-time 6K Image Rescaling with Rate-distortion OptimizationCode1
FastText.zip: Compressing text classification modelsCode1
Context-aware Communication for Multi-agent Reinforcement LearningCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
A Thorough Examination of Decoding Methods in the Era of LLMsCode1
Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and PrivacyCode1
Feature Quantization Improves GAN TrainingCode1
Exploring Frequency-Inspired Optimization in Transformer for Efficient Single Image Super-ResolutionCode1
AdANNS: A Framework for Adaptive Semantic SearchCode1
Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless SystemsCode1
Confounding Tradeoffs for Neural Network QuantizationCode1
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm QuantizerCode1
Designing Large Foundation Models for Efficient Training and Inference: A SurveyCode1
Image Compression with Recurrent Neural Network and Generalized Divisive NormalizationCode1
Inducing Systematicity in Transformers by Attending to Structurally Quantized EmbeddingsCode1
COMQ: A Backpropagation-Free Algorithm for Post-Training QuantizationCode1
CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-ResolutionCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
Conditional Coding and Variable Bitrate for Practical Learned Video CodingCode1
HPTQ: Hardware-Friendly Post Training QuantizationCode1
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNsCode1
HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image RetrievalCode1
HiNeRV: Video Compression with Hierarchical Encoding-based Neural RepresentationCode1
Hybrid Contrastive Quantization for Efficient Cross-View Video RetrievalCode1
And the Bit Goes Down: Revisiting the Quantization of Neural NetworksCode1
Anchor-based Plain Net for Mobile Image Super-ResolutionCode1
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed TrainingCode1
An Automatic Graph Construction Framework based on Large Language Models for RecommendationCode1
Active Image IndexingCode1
Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly DetectionCode1
Hierarchical Quantized AutoencodersCode1
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMsCode1
Hierarchical Vector Quantization for Unsupervised Action SegmentationCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-PrecisionCode1
CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image TranslationCode1
Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code SelectionCode1
Hyper-Compression: Model Compression via HyperfunctionCode1
Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense RetrievalCode1
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and QuantizationCode1
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model MergingCode1
A Benchmark for Gaussian Splatting Compression and Quality Assessment StudyCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural NetworksCode1
CommVQ: Commutative Vector Quantization for KV Cache CompressionCode1
ABCD: Arbitrary Bitwise Coefficient for De-QuantizationCode1
Hard Sample Matters a Lot in Zero-Shot QuantizationCode1
HAWQV3: Dyadic Neural Network QuantizationCode1
Show:102550
← PrevPage 11 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