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 1251–1300 of 4925 papers

TitleStatusHype
Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss—0
Clustering with Bregman Divergences: an Asymptotic Analysis—0
Approximately Invertible Neural Network for Learned Image Compression—0
Adaptive Resolution Inference (ARI): Energy-Efficient Machine Learning for Internet of Things—0
Clustering-Based Evolutionary Federated Multiobjective Optimization and Learning—0
Approximate DCT and Quantization Techniques for Energy-Constrained Image Sensors—0
Cluster-Based Cooperative Digital Over-the-Air Aggregation for Wireless Federated Edge Learning—0
ClusComp: A Simple Paradigm for Model Compression and Efficient Finetuning—0
Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding—0
1-Bit Compressive Sensing for Efficient Federated Learning Over the Air—0
Efficient Compression of Multitask Multilingual Speech Models—0
Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression—0
Accelerating Deep Learning with Dynamic Data Pruning—0
CLIP-Q: Deep Network Compression Learning by In-Parallel Pruning-Quantization—0
Efficient Arbitrary Precision Acceleration for Large Language Models on GPU Tensor Cores—0
Adaptive quantization with mixed-precision based on low-cost proxy—0
2-Bit Random Projections, NonLinear Estimators, and Approximate Near Neighbor Search—0
Efficient Asynchronous Federated Learning with Sparsification and Quantization—0
A Post-coder Feedback Approach to Overcome Training Asymmetry in MIMO-TDD—0
Click-through Rate Prediction with Auto-Quantized Contrastive Learning—0
Adaptive Quantization Resolution and Power Control for Federated Learning over Cell-free Networks—0
Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses—0
Class-based Quantization for Neural Networks—0
Efficient ANN-SNN Conversion with Error Compensation Learning—0
Apollo-Forecast: Overcoming Aliasing and Inference Speed Challenges in Language Models for Time Series Forecasting—0
CLAP-ART: Automated Audio Captioning with Semantic-rich Audio Representation Tokenizer—0
Adaptive Quantization of Neural Networks—0
CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech—0
Accelerating Deep Learning Model Inference on Arm CPUs with Ultra-Low Bit Quantization and Runtime—0
A Planck Radiation and Quantization Scheme for Human Cognition and Language—0
Choose Your Model Size: Any Compression by a Single Gradient Descent—0
Adaptive Quantization of Model Updates for Communication-Efficient Federated Learning—0
Efficient and Workload-Aware LLM Serving via Runtime Layer Swapping and KV Cache Resizing—0
Efficient Batch Homomorphic Encryption for Vertically Federated XGBoost—0
CHIME: A Compressive Framework for Holistic Interest Modeling—0
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models—0
A Picture is Worth a Billion Bits: Real-Time Image Reconstruction from Dense Binary Pixels—0
Cheetah: Mixed Low-Precision Hardware & Software Co-Design Framework for DNNs on the Edge—0
Check-N-Run: A Checkpointing System for Training Deep Learning Recommendation Models—0
Adaptive Quantization for Key Generation in Low-Power Wide-Area Networks—0
Accelerating Deep Learning Inference via Freezing—0
Characterizing the Accuracy -- Efficiency Trade-off of Low-rank Decomposition in Language Models—0
Characterizing Coherent Integrated Photonic Neural Networks under Imperfections—0
APG-MOS: Auditory Perception Guided-MOS Predictor for Synthetic Speech—0
Characterization of the frequency response of channel-interleaved photonic ADCs based on the optical time-division demultiplexer—0
Adaptive Quantization for Deep Neural Network—0
An approach to optimize inference of the DIART speaker diarization pipeline—0
Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference—0
A Performance Analysis of You Only Look Once Models for Deployment on Constrained Computational Edge Devices in Drone Applications—0
Characterising Bias in Compressed Models—0
Show:102550
← PrevPage 26 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