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
Exploiting LLM QuantizationCode1
Object Discovery from Motion-Guided TokensCode1
Exploring the Connection Between Binary and Spiking Neural NetworksCode1
Evaluating the Generalization Ability of Quantized LLMs: Benchmark, Analysis, and ToolboxCode1
4-bit Shampoo for Memory-Efficient Network TrainingCode1
One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning ObjectiveCode1
A Thorough Examination of Decoding Methods in the Era of LLMsCode1
Online Learned Continual Compression with Adaptive Quantization ModulesCode1
AdANNS: A Framework for Adaptive Semantic SearchCode1
Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural NetworksCode1
Evaluation and Optimization of Gradient Compression for Distributed Deep LearningCode1
Error Diffusion: Post Training Quantization with Block-Scaled Number Formats for Neural NetworksCode1
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm QuantizerCode1
EvoPress: Towards Optimal Dynamic Model Compression via Evolutionary SearchCode1
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware TransformationCode1
Enhancing Generalization of Universal Adversarial Perturbation through Gradient AggregationCode1
Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained DevicesCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
Enabling Binary Neural Network Training on the EdgeCode1
EMQ: Evolving Training-free Proxies for Automated Mixed Precision QuantizationCode1
End-to-End Rate-Distortion Optimized 3D Gaussian RepresentationCode1
Embedding in Recommender Systems: A SurveyCode1
End-to-End Rate-Distortion Optimized Learned Hierarchical Bi-Directional Video CompressionCode1
EQ-Net: Elastic Quantization Neural NetworksCode1
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
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMsCode1
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-PrecisionCode1
Efficient and Robust Quantization-aware Training via Adaptive Coreset SelectionCode1
Efficient-VDVAE: Less is moreCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
Graph-less Neural Networks: Teaching Old MLPs New Tricks via DistillationCode1
Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital FossaCode1
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the EdgeCode1
Dynamic Network Quantization for Efficient Video InferenceCode1
A Benchmark for Gaussian Splatting Compression and Quality Assessment StudyCode1
EasyQuant: Post-training Quantization via Scale OptimizationCode1
EFaR 2023: Efficient Face Recognition CompetitionCode1
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D DetectionCode1
DVD-Quant: Data-free Video Diffusion Transformers QuantizationCode1
ABCD: Arbitrary Bitwise Coefficient for De-QuantizationCode1
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
Do Emergent Abilities Exist in Quantized Large Language Models: An Empirical StudyCode1
DNN+NeuroSim V2.0: An End-to-End Benchmarking Framework for Compute-in-Memory Accelerators for On-chip TrainingCode1
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