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 451–500 of 4925 papers

TitleStatusHype
Continual Learning via Bit-Level Information PreservingCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient AdaptationCode1
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model MergingCode1
Compressing LLMs: The Truth is Rarely Pure and Never SimpleCode1
Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital FossaCode1
Adaptive Data-Free QuantizationCode1
Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teachingCode1
Gradient-based Automatic Mixed Precision Quantization for Neural Networks On-ChipCode1
EdgeQAT: Entropy and Distribution Guided Quantization-Aware Training for the Acceleration of Lightweight LLMs on the EdgeCode1
Data-Free Network Quantization With Adversarial Knowledge DistillationCode1
Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware AttentionCode1
Graph Convolutional Network for Recommendation with Low-pass Collaborative FiltersCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
Compress Any Segment Anything Model (SAM)Code1
Abstracted Shapes as Tokens -- A Generalizable and Interpretable Model for Time-series ClassificationCode1
Compression with Bayesian Implicit Neural RepresentationsCode1
A Statistical Framework for Low-bitwidth Training of Deep Neural NetworksCode1
ASTRIDE: Adaptive Symbolization for Time Series DatabasesCode1
MagR: Weight Magnitude Reduction for Enhancing Post-Training QuantizationCode1
Graph-less Neural Networks: Teaching Old MLPs New Tricks via DistillationCode1
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural NetworksCode1
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and QuantizationCode1
Matching-oriented Embedding Quantization For Ad-hoc RetrievalCode1
Geometric Total Variation for Image Vectorization, Zooming and Pixel Art DepixelizingCode1
Animation from Blur: Multi-modal Blur Decomposition with Motion GuidanceCode1
Compact representations of convolutional neural networks via weight pruning and quantizationCode1
Adapting LLaMA Decoder to Vision TransformerCode1
CommVQ: Commutative Vector Quantization for KV Cache CompressionCode1
Genetic Quantization-Aware Approximation for Non-Linear Operations in TransformersCode1
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAECode1
Generative Adversarial Super-Resolution at the Edge with Knowledge DistillationCode1
Communication-Efficient Adaptive Federated LearningCode1
Generalizable Mixed-Precision Quantization via Attribution Rank PreservationCode1
Embedding in Recommender Systems: A SurveyCode1
Generalized Product Quantization Network for Semi-supervised Image RetrievalCode1
Enabling Binary Neural Network Training on the EdgeCode1
EMQ: Evolving Training-free Proxies for Automated Mixed Precision QuantizationCode1
AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic SegmentationCode1
Mind the Gap: A Practical Attack on GGUF QuantizationCode1
Generative De-Quantization for Neural Speech Codec via Latent DiffusionCode1
End-to-End Rate-Distortion Optimized 3D Gaussian RepresentationCode1
AdANNS: A Framework for Adaptive Semantic SearchCode1
EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion ModelsCode1
Comprehensive Graph-conditional Similarity Preserving Network for Unsupervised Cross-modal HashingCode1
CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and QuantizationCode1
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm QuantizerCode1
ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language GenerationCode1
Codebook Features: Sparse and Discrete Interpretability for Neural NetworksCode1
Generative Low-bitwidth Data Free QuantizationCode1
Show:102550
← PrevPage 10 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