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 651–675 of 4925 papers

TitleStatusHype
Anchor-based Plain Net for Mobile Image Super-ResolutionCode1
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed TrainingCode1
BinaryDM: Accurate Weight Binarization for Efficient Diffusion ModelsCode1
Binary Latent DiffusionCode1
EasyQuant: Post-training Quantization via Scale OptimizationCode1
Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital FossaCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
Efficient Quantized Sparse Matrix Operations on Tensor CoresCode1
DVD-Quant: Data-free Video Diffusion Transformers QuantizationCode1
DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationCode1
Hybrid Contrastive Quantization for Efficient Cross-View Video RetrievalCode1
Hyper-Compression: Model Compression via HyperfunctionCode1
EA-3DGS: Efficient and Adaptive 3D Gaussians with Highly Enhanced Quality for outdoor scenesCode1
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D DetectionCode1
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution NetworksCode1
Image Compression with Recurrent Neural Network and Generalized Divisive NormalizationCode1
Catastrophic Failure of LLM Unlearning via QuantizationCode1
Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense RetrievalCode1
Improving Neural Network Efficiency via Post-Training Quantization With Adaptive Floating-PointCode1
Benchmarking of DL Libraries and Models on Mobile DevicesCode1
Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning ApproachCode1
Dynamic Network Quantization for Efficient Video InferenceCode1
A Little Bit More: Bitplane-Wise Bit-Depth RecoveryCode1
Diverse Sample Generation: Pushing the Limit of Generative Data-free QuantizationCode1
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution NetworksCode1
Show:102550
← PrevPage 27 of 197Next →
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