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 1351–1375 of 4925 papers

TitleStatusHype
Bag of Tricks for Optimizing Transformer EfficiencyCode0
DeepShift: Towards Multiplication-Less Neural NetworksCode0
Genie: Show Me the Data for QuantizationCode0
Deep reverse tone mappingCode0
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMsCode0
Deep residual network for steganalysis of digital imagesCode0
Deep Recurrent Quantization for Generating Sequential Binary CodesCode0
GT-SVQ: A Linear-Time Graph Transformer for Node Classification Using Spiking Vector QuantizationCode0
Hierarchical Quantized Representations for Script GenerationCode0
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision WeightsCode0
Deep Priority HashingCode0
MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural NetworksCode0
Deep Optimized Multiple Description Image Coding via Scalar Quantization LearningCode0
Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation RegularizationCode0
Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional ComputingCode0
GANQ: GPU-Adaptive Non-Uniform Quantization for Large Language ModelsCode0
A2Q+: Improving Accumulator-Aware Weight QuantizationCode0
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural ArchitectureCode0
Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model TuningCode0
Deep Neural Network Compression with Single and Multiple Level QuantizationCode0
Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to GiantCode0
FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-designCode0
A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained SettingsCode0
Deep Metric Learning to RankCode0
Generalized Relevance Learning Grassmann QuantizationCode0
Show:102550
← PrevPage 55 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