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 3801–3850 of 4925 papers

TitleStatusHype
AQD: Towards Accurate Fully-Quantized Object DetectionCode1
Experimental results on palmvein-based personal recognition by multi-snapshot fusion of textural features—0
Term Revealing: Furthering Quantization at Run Time on Quantized DNNs—0
Adaptive Periodic Averaging: A Practical Approach to Reducing Communication in Distributed Learning—0
Quantization in Relative Gradient Angle Domain For Building Polygon Estimation—0
SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization—0
AUSN: Approximately Uniform Quantization by Adaptively Superimposing Non-uniform Distribution for Deep Neural Networks—0
Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruning—0
FracBits: Mixed Precision Quantization via Fractional Bit-WidthsCode1
Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights—0
Learning with tree tensor networks: complexity estimates and model selection—0
Learning to Quantize Deep Neural Networks: A Competitive-Collaborative Approach—0
Deep PeNSieve: A deep learning framework based on the posit number systemCode1
Edinburgh's Submissions to the 2020 Machine Translation Efficiency Task—0
Compressing Neural Machine Translation Models with 4-bit Precision—0
EasyQuant: Post-training Quantization via Scale OptimizationCode1
Robust Product Markovian Quantization—0
Graph Convolutional Network for Recommendation with Low-pass Collaborative FiltersCode1
Making DensePose fast and lightCode1
Bit Error Robustness for Energy-Efficient DNN AcceleratorsCode0
Unsupervised Cross-lingual Representation Learning for Speech RecognitionCode1
Lattice Representation Learning—0
Multi-Class Uncertainty Calibration via Mutual Information Maximization-based BinningCode0
Exploiting Weight Redundancy in CNNs: Beyond Pruning and Quantization—0
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression—0
Efficient Integer-Arithmetic-Only Convolutional Neural NetworksCode0
Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization—0
wav2vec 2.0: A Framework for Self-Supervised Learning of Speech RepresentationsCode3
DEED: A General Quantization Scheme for Communication Efficiency in Bits—0
COVIDLite: A depth-wise separable deep neural network with white balance and CLAHE for detection of COVID-19—0
Some useful approximations for calculation of directivities of multibeam power patterns of large planar arrays—0
Efficient Execution of Quantized Deep Learning Models: A Compiler Approach—0
Federated Learning With Quantized Global Model Updates—0
FrostNet: Towards Quantization-Aware Network Architecture SearchCode1
Universally Quantized Neural Compression—0
Quantization of Acoustic Model Parameters in Automatic Speech Recognition Framework—0
CNN Acceleration by Low-rank Approximation with Quantized Factors—0
Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectorsCode1
HyperFlow: Representing 3D Objects as SurfacesCode0
Neural gradients are near-lognormal: improved quantized and sparse training—0
APQ: Joint Search for Network Architecture, Pruning and Quantization PolicyCode1
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer ProgrammingCode1
Sparsity Turns Adversarial: Energy and Latency Attacks on Deep Neural Networks—0
O(1) Communication for Distributed SGD through Two-Level Gradient Averaging—0
Noisy One-bit Compressed Sensing with Side-Information—0
Neural Network Activation Quantization with Bitwise Information BottlenecksCode0
Knowledge Distillation: A Survey—0
VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architectureCode1
Generative Design of Hardware-aware DNNs—0
UVeQFed: Universal Vector Quantization for Federated LearningCode1
Show:102550
← PrevPage 77 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