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 2726–2750 of 4925 papers

TitleStatusHype
DeepliteRT: Computer Vision at the Edge—0
Deep Model Compression Via Two-Stage Deep Reinforcement Learning—0
Deep Multi-modality Soft-decoding of Very Low Bit-rate Face Videos—0
Deep Multiple Description Coding by Learning Scalar Quantization—0
Deep Neural Network-Based Quantized Signal Reconstruction for DOA Estimation—0
Deep Neural Network Capacity—0
Deep Neural Network Models Compression—0
Deep neural networks algorithms for stochastic control problems on finite horizon: numerical applications—0
Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis—0
Deep neural networks are robust to weight binarization and other non-linear distortions—0
Deep Perceptual Preprocessing for Video Coding—0
Deep Quantization: Encoding Convolutional Activations with Deep Generative Model—0
Deep Residual Hashing—0
Deep Saliency Hashing—0
Deep Signal Recovery with One-Bit Quantization—0
Deep Spherical Quantization for Image Search—0
Deep Task-Based Quantization—0
DeepTwist: Learning Model Compression via Occasional Weight Distortion—0
Deep Unfolding with Kernel-based Quantization in MIMO Detection—0
Deep Unsupervised Learning for Joint Antenna Selection and Hybrid Beamforming—0
Deep Visual-Semantic Quantization for Efficient Image Retrieval—0
Defend Deep Neural Networks Against Adversarial Examples via Fixed and Dynamic Quantized Activation Functions—0
Defensive Quantization: When Efficiency Meets Robustness—0
Degree-Quant: Quantization-Aware Training for Graph Neural Networks—0
DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization—0
Show:102550
← PrevPage 110 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