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 2751–2800 of 4925 papers

TitleStatusHype
Knowledge Distillation in Vision Transformers: A Critical Review—0
UW-CVGAN: UnderWater Image Enhancement with Capsules Vectors Quantization—0
Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search—0
Disco Intelligent Reflecting Surfaces: Active Channel Aging for Fully-Passive Jamming Attacks—0
Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance—0
Efficient and Effective Methods for Mixed Precision Neural Network Quantization for Faster, Energy-efficient Inference—0
Parsimonious System Identification from Fragmented Quantized Measurements—0
State Machine-based Waveforms for Channels With 1-Bit Quantization and Oversampling With Time-Instance Zero-Crossing Modulation—0
Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases—0
Hardware Implementation of Task-based Quantization in Multi-user Signal Recovery—0
Quantized Deep Path-following Control on a Microcontroller—0
BOMP-NAS: Bayesian Optimization Mixed Precision NAS—0
PowerQuant: Automorphism Search for Non-Uniform Quantization—0
Victoria Amazonica Optimization (VAO): An Algorithm Inspired by the Giant Water Lily PlantCode0
Optimized learned entropy coding parameters for practical neural-based image and video compression—0
Learning Frequency-Specific Quantization Scaling in VVC for Standard-Compliant Task-driven Image CodingCode0
Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI FeedbackCode0
Robust Symbol Level Precoding for Overlay Cognitive Radio Networks—0
ACQ: Improving Generative Data-free Quantization Via Attention Correction—0
HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble—0
Development, Optimization, and Deployment of Thermal Forward Vision Systems for Advance Vehicular Applications on Edge DevicesCode0
Deep Conditional Measure Quantization—0
Masked Vector Quantization—0
RedBit: An End-to-End Flexible Framework for Evaluating the Accuracy of Quantized CNNsCode0
Semantic and Effective Communication for Remote Control Tasks with Dynamic Feature Compression—0
Exploring Automatic Gym Workouts Recognition Locally On Wearable Resource-Constrained Devices—0
Security-Aware Approximate Spiking Neural Networks—0
UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion—0
Transceiver Cooperative Learning-aided Semantic Communications Against Mismatched Background Knowledge Bases—0
Does compressing activations help model parallel training?—0
Graph-Collaborated Auto-Encoder Hashing for Multi-view Binary Clustering—0
Automating Nearest Neighbor Search Configuration with Constrained Optimization—0
Reduced Reference Quality Assessment for Point Cloud Compression—0
Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning—0
Overcoming Forgetting Catastrophe in Quantization-Aware Training—0
Rethinking Few-Shot Medical Segmentation: A Vector Quantization View—0
One-Shot Model for Mixed-Precision Quantization—0
Adverse Weather Removal with Codebook Priors—0
Video Compression With Entropy-Constrained Neural Representations—0
Unsupervised Facial Performance Editing via Vector-Quantized StyleGAN Representations—0
SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers—0
Deep Hashing With Minimal-Distance-Separated Hash Centers—0
Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization—0
Toward Accurate Post-Training Quantization for Image Super ResolutionCode0
Disentangled Representation Learning for Unsupervised Neural Quantization—0
Vector Quantization With Self-Attention for Quality-Independent Representation Learning—0
NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-wise ModelingCode0
Quantizing Heavy-tailed Data in Statistical Estimation: (Near) Minimax Rates, Covariate Quantization, and Uniform Recovery—0
Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling—0
Biologically Plausible Learning on Neuromorphic Hardware Architectures—0
Show:102550
← PrevPage 56 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