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 4701–4750 of 4925 papers

TitleStatusHype
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning—0
SEP-Nets: Small and Effective Pattern Networks—0
ShiftCNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural NetworksCode0
3D Pathfinding and Collision Avoidance Using Uneven Search-space Quantization and Visual Cone Search—0
Image Compression Based on Compressive Sensing: End-to-End Comparison with JPEG—0
A Vision System for Multi-View Face Recognition—0
Residual Expansion Algorithm: Fast and Effective Optimization for Nonconvex Least Squares Problems—0
Detecting Adversarial Image Examples in Deep Networks with Adaptive Noise ReductionCode0
LCDet: Low-Complexity Fully-Convolutional Neural Networks for Object Detection in Embedded Systems—0
Incremental Learning Through Deep Adaptation—0
Compressive Estimation of a Stochastic Process with Unknown Autocorrelation Function—0
Robust tracking of respiratory rate in high-dynamic range scenes using mobile thermal imaging—0
Learning of Gaussian Processes in Distributed and Communication Limited Systems—0
Algorithmic trading in a microstructural limit order book model—0
Ternary Neural Networks with Fine-Grained Quantization—0
Regularized Residual Quantization: a multi-layer sparse dictionary learning approach—0
Acoustic Model Compression with MAP adaptation—0
Accelerated Nearest Neighbor Search with Quick ADCCode0
PQTable: Non-exhaustive Fast Search for Product-quantized Codes using Hash Tables—0
WRPN: Training and Inference using Wide Reduced-Precision Networks—0
Pyramid Vector Quantization for Deep Learning—0
Enhance Feature Discrimination for Unsupervised Hashing—0
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations—0
Asymmetric Learning Vector Quantization for Efficient Nearest Neighbor Classification in Dynamic Time Warping Spaces—0
A Bag-of-Words Equivalent Recurrent Neural Network for Action RecognitionCode0
End-to-end Binary Representation Learning via Direct Binary Embedding—0
Guetzli: Perceptually Guided JPEG EncoderCode0
Don't Fear the Bit Flips: Optimized Coding Strategies for Binary Classification—0
Unsupervised Triplet Hashing for Fast Image Retrieval—0
Fixed-point optimization of deep neural networks with adaptive step size retraining—0
Memory-Efficient Global Refinement of Decision-Tree Ensembles and its Application to Face Alignment—0
Low-Precision Batch-Normalized Activations—0
Efficient Large-scale Approximate Nearest Neighbor Search on the GPUCode0
Soft Weight-Sharing for Neural Network CompressionCode0
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision WeightsCode0
Hashing in the Zero Shot Framework with Domain Adaptation—0
Deep Learning with Low Precision by Half-wave Gaussian QuantizationCode0
Mixed Low-precision Deep Learning Inference using Dynamic Fixed Point—0
Scalable Nearest Neighbor Search based on kNN Graph—0
Compression of Deep Neural Networks for Image Instance Retrieval—0
Automated Linear-Time Detection and Quality Assessment of Superpixels in Uncalibrated True- or False-Color RGB Images—0
Classification Accuracy Improvement for Neuromorphic Computing Systems with One-level Precision Synapses—0
Distinguishing Posed and Spontaneous Smiles by Facial Dynamics—0
Mixed one-bit compressive sensing with applications to overexposure correction for CT reconstruction—0
Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection—0
Deep Residual Hashing—0
Understanding the Impact of Precision Quantization on the Accuracy and Energy of Neural Networks—0
Towards the Limit of Network Quantization—0
ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA—0
Quantized Random Projections and Non-Linear Estimation of Cosine Similarity—0
Show:102550
← PrevPage 95 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