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 4601–4650 of 4925 papers

TitleStatusHype
Fisher-aware Quantization for DETR Detectors with Critical-category Objectives—0
FIT: A Metric for Model Sensitivity—0
FIXAR: A Fixed-Point Deep Reinforcement Learning Platform with Quantization-Aware Training and Adaptive Parallelism—0
Fixed-Point Back-Propagation Training—0
Fixed-point optimization of deep neural networks with adaptive step size retraining—0
Fixed-Point Performance Analysis of Recurrent Neural Networks—0
Fixed-point quantization aware training for on-device keyword-spotting—0
Fixed Point Quantization of Deep Convolutional Networks—0
Fixflow: A Framework to Evaluate Fixed-point Arithmetic in Light-Weight CNN Inference—0
FLARE: FP-Less PTQ and Low-ENOB ADC Based AMS-PiM for Error-Resilient, Fast, and Efficient Transformer Acceleration—0
FlashAttention on a Napkin: A Diagrammatic Approach to Deep Learning IO-Awareness—0
FlatENN: Train Flat for Enhanced Fault Tolerance of Quantized Deep Neural Networks—0
Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance—0
FlattenQuant: Breaking Through the Inference Compute-bound for Large Language Models with Per-tensor Quantization—0
Flexible Neural Image Compression via Code Editing—0
Flexible Unsupervised Learning for Massive MIMO Subarray Hybrid Beamforming—0
FleXOR: Trainable Fractional Quantization—0
FlexQuant: Elastic Quantization Framework for Locally Hosted LLM on Edge Devices—0
FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs—0
FLightNNs: Lightweight Quantized Deep Neural Networks for Fast and Accurate Inference—0
FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search—0
FlowPrecision: Advancing FPGA-Based Real-Time Fluid Flow Estimation with Linear Quantization—0
FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization—0
FoldToken2: Learning compact, invariant and generative protein structure language—0
FoldToken: Learning Protein Language via Vector Quantization and Beyond—0
Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks—0
Forearm Ultrasound based Gesture Recognition on Edge—0
Formal Uncertainty Propagation for Stochastic Dynamical Systems with Additive Noise—0
Forward Link Analysis for Full-Duplex Cellular Networks with Low Resolution ADC/DAC—0
Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own—0
FoVolNet: Fast Volume Rendering using Foveated Deep Neural Networks—0
FP8-BERT: Post-Training Quantization for Transformer—0
FP8 versus INT8 for efficient deep learning inference—0
FPGA Implementations of Layered MinSum LDPC Decoders Using RCQ Message Passing—0
FPGA Resource-aware Structured Pruning for Real-Time Neural Networks—0
FPRaker: A Processing Element For Accelerating Neural Network Training—0
FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion—0
FPTQ: Fine-grained Post-Training Quantization for Large Language Models—0
FPTQuant: Function-Preserving Transforms for LLM Quantization—0
FP=xINT:A Low-Bit Series Expansion Algorithm for Post-Training Quantization—0
FQ-Conv: Fully Quantized Convolution for Efficient and Accurate Inference—0
Frame Quantization of Neural Networks—0
Free Bits: Latency Optimization of Mixed-Precision Quantized Neural Networks on the Edge—0
freePruner: A Training-free Approach for Large Multimodal Model Acceleration—0
Frequency Autoregressive Image Generation with Continuous Tokens—0
Frequency-Biased Synergistic Design for Image Compression and Compensation—0
Frequency Disentangled Features in Neural Image Compression—0
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks—0
From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference—0
From Large to Super-Tiny: End-to-End Optimization for Cost-Efficient LLMs—0
Show:102550
← PrevPage 93 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