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 1301–1325 of 4925 papers

TitleStatusHype
2-bit Conformer quantization for automatic speech recognition—0
Channel-Wise Mixed-Precision Quantization for Large Language Models—0
APCodec+: A Spectrum-Coding-Based High-Fidelity and High-Compression-Rate Neural Audio Codec with Staged Training Paradigm—0
Adaptive Proximal Gradient Methods for Structured Neural Networks—0
Efficient FPGA-accelerated Convolutional Neural Networks for Cloud Detection on CubeSats—0
Channel-wise Hessian Aware trace-Weighted Quantization of Neural Networks—0
Channel Pruning In Quantization-aware Training: An Adaptive Projection-gradient Descent-shrinkage-splitting Method—0
Channel Estimation in MIMO Systems with One-bit Spatial Sigma-delta ADCs—0
APack: Off-Chip, Lossless Data Compression for Efficient Deep Learning Inference—0
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens—0
Efficient Hybrid Network Architectures for Extremely Quantized Neural Networks Enabling Intelligence at the Edge—0
Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks—0
End-to-End Neural Network Compression via _1_2 Regularized Latency Surrogates—0
Channel Estimation for MIMO Hybrid Architectures with Low Resolution ADCs for mmWave Communication—0
Channel Balancing for Accurate Quantization of Winograd Convolutions—0
Channel-Aware Constellation Design for Digital OTA Computation—0
Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers—0
HAWKEYE: Adversarial Example Detector for Deep Neural Networks—0
Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference—0
Order of Compression: A Systematic and Optimal Sequence to Combinationally Compress CNN—0
An Ultra-Efficient Memristor-Based DNN Framework with Structured Weight Pruning and Quantization Using ADMM—0
ANTLER: Bayesian Nonlinear Tensor Learning and Modeler for Unstructured, Varying-Size Point Cloud Data—0
Cell growth rate dictates the onset of glass to fluid-like transition and long time super-diffusion in an evolving cell colony—0
Adaptive Periodic Averaging: A Practical Approach to Reducing Communication in Distributed Learning—0
Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing—0
Show:102550
← PrevPage 53 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