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 4751–4800 of 4925 papers

TitleStatusHype
Cross-Modal Epileptic Signal Harmonization: Frequency Domain Mapping Quantization for Pre-training a Unified Neurophysiological TransformerCode0
Uncovering the Hidden Cost of Model CompressionCode0
Power Law Graph Transformer for Machine Translation and Representation LearningCode0
The Cost of Compression: Investigating the Impact of Compression on Parametric Knowledge in Language ModelsCode0
Vector and Line Quantization for Billion-scale Similarity Search on GPUsCode0
HQOD: Harmonious Quantization for Object DetectionCode0
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure AggregationCode0
PP-ShiTu: A Practical Lightweight Image Recognition SystemCode0
The Ecological Footprint of Neural Machine Translation SystemsCode0
Effective Quantization Methods for Recurrent Neural NetworksCode0
Effective Communication with Dynamic Feature CompressionCode0
Training Thinner and Deeper Neural Networks: Jumpstart RegularizationCode0
The Effect of Points Dispersion on the k-nn Search in Random Projection ForestsCode0
PQV-Mobile: A Combined Pruning and Quantization Toolkit to Optimize Vision Transformers for Mobile ApplicationsCode0
HyperFlow: Representing 3D Objects as SurfacesCode0
EdgeProfiler: A Fast Profiling Framework for Lightweight LLMs on Edge Using Analytical ModelCode0
The Effect of Points Dispersion on the k-nn Search in Random Projection ForestsCode0
Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to GiantCode0
Sparsified SGD with MemoryCode0
Resource Constrained Semantic Segmentation for Waste SortingCode0
Cauchy-Schwarz RegularizersCode0
Resource-efficient DNNs for Keyword Spotting using Neural Architecture Search and QuantizationCode0
CQIL: Inference Latency Optimization with Concurrent Computation of Quasi-Independent LayersCode0
The HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal StatesCode0
Hybrid coarse-fine classification for head pose estimationCode0
CAT: Compression-Aware Training for bandwidth reductionCode0
Resource-Efficient Speech Quality Prediction through Quantization Aware Training and Binary Activation MapsCode0
APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-DesignCode0
EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector QuantizationCode0
ECQ^x: Explainability-Driven Quantization for Low-Bit and Sparse DNNsCode0
The Impact of Inference Acceleration Strategies on Bias of LLMsCode0
A Programmable Approach to Neural Network CompressionCode0
ECG Beats Fast Classification Base on Sparse DictionariesCode0
A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained SettingsCode0
ECG beats classification via online sparse dictionary and time pyramid matchingCode0
Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language ModelsCode0
Rethinking Data-Free Quantization as a Zero-Sum GameCode0
Transductive Zero-Shot Hashing for Multilabel Image RetrievalCode0
Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and MemoryCode0
All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image ClassificationCode0
The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantizationCode0
Approximate spectral clustering using both reference vectors and topology of the network generated by growing neural gasCode0
Coresets for Archetypal AnalysisCode0
HOT: Hadamard-based Optimized TrainingCode0
PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home ClustersCode0
Primary quantization matrix estimation of double compressed JPEG images via CNNCode0
Homology-constrained vector quantization entropy regularizerCode0
PRISM: Privacy-Preserving Improved Stochastic Masking for Federated Generative ModelsCode0
Privacy-Aware Randomized Quantization via Linear ProgrammingCode0
Highly Optimized Kernels and Fine-Grained Codebooks for LLM Inference on Arm CPUsCode0
Show:102550
← PrevPage 96 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